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

    Neuronpedia

    INDEX
    Explanations

    ist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trick
    -0.07
    osten
    -0.06
    inz
    -0.06
     dramatically
    -0.06
     carbon
    -0.06
     kettle
    -0.06
     cocina
    -0.06
    acao
    -0.06
    DEL
    -0.06
    913
    -0.06
    POSITIVE LOGITS
     humanities
    0.21
     Humanities
    0.19
    selectorMethod
    0.07
    Immutable
    0.07
     thous
    0.07
     SimpleDateFormat
    0.07
    太阳城
    0.07
     LOGIN
    0.06
     princ
    0.06
    되는
    0.06
    Act Density 0.003%

    No Known Activations