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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (schedule
    -0.07
     системи
    -0.06
     fou
    -0.06
     ray
    -0.06
    _statement
    -0.06
     alcan
    -0.06
    oped
    -0.06
     nast
    -0.06
     unbearable
    -0.06
    iton
    -0.06
    POSITIVE LOGITS
     української
    0.07
    好き
    0.06
    .Serialize
    0.06
    їв
    0.06
     gaan
    0.06
    ành
    0.06
    ic
    0.06
    	request
    0.06
    ีความ
    0.06
     proč
    0.06
    Act Density 0.001%

    No Known Activations