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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wend
    -0.07
     آب
    -0.07
     дв
    -0.06
    (dict
    -0.06
    _mtx
    -0.06
     طول
    -0.06
     Rad
    -0.06
    歩
    -0.06
     karış
    -0.06
    ไลน
    -0.06
    POSITIVE LOGITS
     Mini
    0.07
     visibly
    0.07
    [R
    0.06
     Majority
    0.06
    ……
    0.06
    contri
    0.06
    	Logger
    0.06
    esser
    0.06
    def
    0.06
    народ
    0.06
    Act Density 0.042%

    No Known Activations