Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming language constructs, particularly access modifiers and class-related declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Abbreviations or initialisms

    np_acts-logits-general · gemini-2.0-flash

    HSP interactors or diffs2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heretics
    -0.47
    _
    -0.46
     Puoi
    -0.44
     Turi
    -0.44
     Avila
    -0.44
     TLS
    -0.43
     treasure
    -0.43
     effect
    -0.43
     Eucalyptus
    -0.41
    effect
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    1.06
    tvguidetime
    1.01
    LookAnd
    1.00
    ftagPool
    0.93
    hyrchwyd
    0.92
    GEBURTSDATUM
    0.85
    abestanden
    0.84
    ParallelGroup
    0.83
     ProtoMessage
    0.83
    ⓧ
    0.83
    Act Density 0.044%

    No Known Activations