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

    Neuronpedia

    INDEX
    Explanations

    Informal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sch
    -0.07
    ‌کن
    -0.06
    reward
    -0.06
     hab
    -0.06
     위치
    -0.06
    +d
    -0.06
    OLDER
    -0.06
     addSubview
    -0.06
     literal
    -0.06
    Land
    -0.06
    POSITIVE LOGITS
    _MR
    0.06
    IllegalArgumentException
    0.06
    tbody
    0.06
    .goods
    0.06
     Baton
    0.06
     upgrade
    0.06
     prick
    0.06
     prueba
    0.06
     underestimate
    0.06
    _merge
    0.06
    Act Density 0.005%

    No Known Activations