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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal honesty or sincerity

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

    honestly say/don't/think/thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.81
    Демографія
    -0.50
    ſelf
    -0.49
    dagogik
    -0.48
    EndContext
    -0.47
     Kontext
    -0.47
     perfons
    -0.47
    transQ
    -0.46
     Chrift
    -0.46
    antaranya
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.47
    setVerticalGroup
    0.45
     HasFactory
    0.41
    AppCompat
    0.39
    <bos>
    0.39
    cense
    0.38
    IUrlHelper
    0.38
     toa
    0.37
    所の
    0.37
    BufferException
    0.37
    Act Density 0.008%

    No Known Activations