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
    158
    -0.07
    )arg
    -0.07
     Đo
    -0.06
    _columns
    -0.06
    Containers
    -0.06
    Slf
    -0.06
    Vault
    -0.06
    .stats
    -0.05
    Surface
    -0.05
    قت
    -0.05
    POSITIVE LOGITS
    pr
    0.07
     seguridad
    0.07
     konum
    0.06
    .character
    0.06
    }.${
    0.06
    ocusing
    0.06
    سي
    0.06
    	js
    0.06
    _Label
    0.06
     پر
    0.06
    Act Density 0.000%

    No Known Activations