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

    Neuronpedia

    INDEX
    Explanations

    elements related to discussions and reflections on past events

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

    preceding a verb or auxiliary verb

    np_acts-logits-general · gemini-2.0-flash

    Graves claimed, unwittingly supplied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.70
    ésult
    -0.66
    twimg
    -0.65
    LEncoder
    -0.64
    LookAnd
    -0.64
    EndProject
    -0.63
     '\\;'
    -0.60
    ientí
    -0.59
     internetowa
    -0.59
    PhysRev
    -0.58
    POSITIVE LOGITS
    Readers
    0.56
     evidently
    0.55
     polem
    0.53
     pasaje
    0.52
     centrale
    0.52
     hinting
    0.50
     passages
    0.50
     halla
    0.50
     teasing
    0.49
     centrales
    0.48
    Act Density 0.676%

    No Known Activations