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

    Neuronpedia

    INDEX
    Explanations

    say quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    duct
    -0.08
    .OP
    -0.07
     Manage
    -0.07
    运转
    -0.07
    订
    -0.07
    CONTENT
    -0.07
    了一会儿
    -0.07
    ⛳
    -0.06
    榖
    -0.06
     beginners
    -0.06
    POSITIVE LOGITS
     Palestin
    0.07
    иг
    0.06
     Freedom
    0.06
    _style
    0.06
    貴
    0.06
     odp
    0.06
    저
    0.06
     Away
    0.06
    _IT
    0.06
    object
    0.06
    Act Density 0.003%

    No Known Activations