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

    Neuronpedia

    INDEX
    Explanations

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stride
    -0.08
     بلا
    -0.07
     thee
    -0.07
    ely
    -0.07
     מס
    -0.07
     TextInputType
    -0.07
    _lim
    -0.07
    textInput
    -0.06
    itable
    -0.06
    Consult
    -0.06
    POSITIVE LOGITS
     dopo
    0.07
    werp
    0.07
    ☳
    0.07
    \C
    0.07
     pilot
    0.07
    电站
    0.06
     decisión
    0.06
    Poor
    0.06
    brero
    0.06
    rgan
    0.06
    Act Density 0.002%

    No Known Activations