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

    Neuronpedia

    INDEX
    Explanations

    ,$

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خی
    -0.07
     highlighted
    -0.06
     Riders
    -0.06
     Indones
    -0.06
     nouveaux
    -0.06
    зация
    -0.06
    %，
    -0.06
    GLIGENCE
    -0.06
     این
    -0.06
     hos
    -0.06
    POSITIVE LOGITS
    ardo
    0.06
     Donald
    0.06
     skirm
    0.06
    rends
    0.06
    _streams
    0.06
     obvykle
    0.06
    KERNEL
    0.06
    iagnostics
    0.06
     神马
    0.06
    atters
    0.06
    Act Density 0.000%

    No Known Activations