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

    Neuronpedia

    INDEX
    Explanations

    none of the relevant context

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

    Code, math, or uncommon words

    np_acts-logits-general · gemini-2.0-flash

    descriptions of bathrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.72
     TextAppearance
    -0.57
    intellij
    -0.54
    DockStyle
    -0.53
    Advertisements
    -0.53
    Personendaten
    -0.51
     auszu
    -0.50
    <?
    -0.50
    ʺ
    -0.49
     "..\..\
    -0.49
    POSITIVE LOGITS
    tvguidetime
    0.85
    Personensuche
    0.59
    BeginContext
    0.57
     Amor
    0.55
    Amor
    0.51
     rẻ
    0.50
    RTRS
    0.50
    sscanf
    0.49
    diri
    0.49
    tonode
    0.49
    Act Density 0.015%

    No Known Activations