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

    Neuronpedia

    INDEX
    Explanations

    hob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    []↵
    -0.07
    ṿ
    -0.07
    вор
    -0.07
    tn
    -0.07
     naz
    -0.07
    Վ
    -0.07
    ッ
    -0.06
    fonts
    -0.06
    党总
    -0.06
    风吹
    -0.06
    POSITIVE LOGITS
    chedule
    0.08
    总是
    0.07
     hap
    0.07
    /business
    0.07
    (tuple
    0.07
     مست
    0.07
     TABLE
    0.07
    _Module
    0.07
     nominal
    0.07
    向外
    0.07
    Act Density 0.002%

    No Known Activations