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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and other types of delimiters

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

    "$Id:" followed by file names

    np_acts-logits-general · gemini-2.0-flash

    version $Id identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    haft
    -0.50
     مواليد
    -0.47
    äsident
    -0.47
     Protobuf
    -0.46
     –
    -0.45
    DatabaseError
    -0.45
     Bernstein
    -0.45
    eff
    -0.44
     itself
    -0.43
     ktor
    -0.43
    POSITIVE LOGITS
    adaptiveStyles
    0.91
     Majefty
    0.89
    tvguidetime
    0.84
     houſe
    0.83
    发表于
    0.80
     Anſ
    0.80
     Theſe
    0.77
     pleaſure
    0.73
     becauſe
    0.72
     Houſe
    0.71
    Act Density 0.011%

    No Known Activations