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

    Neuronpedia

    INDEX
    Explanations

    seem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     S
    -0.06
     cứ
    -0.06
     Booking
    -0.06
     vlast
    -0.06
     ONE
    -0.06
    위
    -0.06
     tespit
    -0.06
     Fischer
    -0.06
     attributes
    -0.06
    categorias
    -0.06
    POSITIVE LOGITS
    .parseFloat
    0.07
     Kg
    0.07
    fsp
    0.07
    .SelectCommand
    0.07
    モ
    0.06
    ?=.*
    0.06
    uş
    0.06
     Phó
    0.06
     NSStringFromClass
    0.06
    _ls
    0.06
    Act Density 0.013%

    No Known Activations