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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Amount
    -0.08
    汆
    -0.07
    ruk
    -0.07
    /values
    -0.07
    uye
    -0.07
    独一
    -0.07
    uat
    -0.06
    Ế
    -0.06
    _uploaded
    -0.06
     LOD
    -0.06
    POSITIVE LOGITS
    (full
    0.08
     sparking
    0.07
    /black
    0.07
     اللجنة
    0.07
     Iris
    0.07
     ),
↵
    0.07
    ocial
    0.07
    icz
    0.07
    带着
    0.07
    chestra
    0.07
    Act Density 0.003%

    No Known Activations