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

    Neuronpedia

    INDEX
    Explanations

    -induced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stra
    -0.07
    #
↵
    -0.07
     String
    -0.06
     commun
    -0.06
    итор
    -0.06
    าต
    -0.06
    编号
    -0.06
     knobs
    -0.06
     hern
    -0.06
     booking
    -0.06
    POSITIVE LOGITS
     induced
    0.07
    šen
    0.07
    _LONG
    0.07
    -induced
    0.07
    ]");↵
    0.06
    _CELL
    0.06
    _OUTPUT
    0.06
    liğinde
    0.06
    _escape
    0.06
    .fixed
    0.06
    Act Density 0.005%

    No Known Activations