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

    Neuronpedia

    INDEX
    Explanations

    sequences of digits or numerical values

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

    Convert, What, Dump, Model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -1.00
     تضيفلها
    -0.84
    uxxxx
    -0.81
    expandindo
    -0.80
    findpost
    -0.79
    RenderAtEndOf
    -0.79
     snippetHide
    -0.77
     <<<<<<<<<<<<<<
    -0.75
    principalColumn
    -0.75
    -0.75
    POSITIVE LOGITS
     
    0.42
    ↵
    0.41
     I
    0.40
     is
    0.39
     Fischer
    0.36
    ’
    0.36
     man
    0.35
     lie
    0.35
    <bos>
    0.35
     it
    0.35
    Act Density 0.001%

    No Known Activations