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

    Neuronpedia

    INDEX
    Explanations

    c code

    oai_token-act-pair · gemini-2.0-flash

    diagnostic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     themſelves
    -0.77
     myſelf
    -0.70
     itſelf
    -0.69
     TimeUnit
    -0.68
     Efq
    -0.66
     насељу
    -0.65
    astify
    -0.64
     Monfieur
    -0.64
    invokeLater
    -0.64
    kloped
    -0.63
    POSITIVE LOGITS
    DoubleQuotes
    0.63
    ReusableCell
    0.49
     WARS
    0.47
    CommandText
    0.47
     Geografía
    0.45
    psu
    0.44
     пона
    0.42
    WriteLiteral
    0.42
     numeros
    0.41
    ensões
    0.41
    Act Density 0.879%

    No Known Activations