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

    Neuronpedia

    INDEX
    Explanations

    code, configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tantra
    -0.07
     několik
    -0.07
    Hierarchy
    -0.07
     STA
    -0.07
     Parcel
    -0.06
     celý
    -0.06
    Ana
    -0.06
    _CONTROLLER
    -0.06
     selv
    -0.06
     nằm
    -0.06
    POSITIVE LOGITS
    posed
    0.07
    aling
    0.07
    inner
    0.07
     regimen
    0.06
     salute
    0.06
    _with
    0.06
     coerce
    0.06
    avez
    0.06
    cket
    0.06
    択
    0.06
    Act Density 0.128%

    No Known Activations