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
    <count
    -0.07
     hå
    -0.07
     Construction
    -0.07
    楽
    -0.07
    用户名
    -0.06
     مخ
    -0.06
     convin
    -0.06
     objectType
    -0.06
     мг
    -0.06
    _detection
    -0.06
    POSITIVE LOGITS
     　
    0.06
    ?s
    0.06
    olves
    0.06
    kých
    0.06
    ABI
    0.06
    ovaná
    0.06
     paginator
    0.06
    opts
    0.06
    ovaného
    0.06
     ries
    0.06
    Act Density 0.009%

    No Known Activations