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

    Neuronpedia

    INDEX
    Explanations

    It

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .form
    -0.08
     позвол
    -0.06
     prostate
    -0.06
    ]%
    -0.06
    ация
    -0.06
    ьми
    -0.06
    privation
    -0.06
    mdp
    -0.06
    �
    -0.06
     benzer
    -0.06
    POSITIVE LOGITS
     Count
    0.07
    часно
    0.06
     Laz
    0.06
     콜
    0.06
    _ACTIV
    0.06
    JOIN
    0.06
     Fluid
    0.06
     Firefox
    0.06
    اش
    0.06
    ek
    0.06
    Act Density 0.029%

    No Known Activations