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

    Neuronpedia

    INDEX
    Explanations

    density

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bout
    -0.07
    .Man
    -0.07
    好的
    -0.06
     Ret
    -0.06
    isiert
    -0.06
    @include
    -0.06
     Rog
    -0.06
     Pick
    -0.06
    ôn
    -0.06
    ours
    -0.06
    POSITIVE LOGITS
     ));
    0.06
    ednou
    0.06
     стоимость
    0.06
     amph
    0.06
    ές
    0.06
     plumbing
    0.06
     Комп
    0.06
     sie
    0.06
    roat
    0.06
     constitu
    0.06
    Act Density 0.005%

    No Known Activations