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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace or empty characters

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

    Nginx probe functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kariera
    -0.54
     and
    -0.49
     /
    -0.46
    }{*}{
    -0.45
     viewpoint
    -0.45
    /
    -0.45
    iken
    -0.44
    lices
    -0.43
    itudine
    -0.43
     ràng
    -0.43
    POSITIVE LOGITS
     kaarangay
    0.57
    parsedMessage
    0.56
     tartalomajánló
    0.53
    uxxxx
    0.51
     iconLine
    0.49
    NUMX
    0.46
    цездатний
    0.45
    expandindo
    0.43
    səhifə
    0.42
    UnknownFieldSet
    0.41
    Act Density 0.005%

    No Known Activations