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

    Neuronpedia

    INDEX
    Explanations

    Images

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izon
    -0.07
    亓
    -0.07
    GHz
    -0.07
    躺在
    -0.06
    تويتر
    -0.06
     dirname
    -0.06
    /Area
    -0.06
     Felix
    -0.06
    报纸
    -0.06
     Sammy
    -0.06
    POSITIVE LOGITS
    빪
    0.07
    ساط
    0.07
    ประเม
    0.07
    .ident
    0.06
     originals
    0.06
    _();↵
    0.06
    .Payload
    0.06
    ByKey
    0.06
    _cf
    0.06
     usage
    0.06
    Act Density 0.001%

    No Known Activations