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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Channel
    -0.07
     responder
    -0.07
    _Cell
    -0.06
    /client
    -0.06
     дых
    -0.06
    registers
    -0.06
     RSA
    -0.06
    /pm
    -0.06
     controversy
    -0.06
    liqu
    -0.06
    POSITIVE LOGITS
     rental
    0.07
    .ComboBox
    0.07
     suma
    0.06
     Judaism
    0.06
     созда
    0.06
    _predicate
    0.06
    dart
    0.06
     vita
    0.06
    、あ
    0.06
     geliştir
    0.06
    Act Density 0.058%

    No Known Activations