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

    Neuronpedia

    INDEX
    Explanations

    features and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Substituting
    0.84
     depriving
    0.82
     conundrum
    0.79
     chied
    0.78
     asking
    0.78
     الاستفهام
    0.77
     pytanie
    0.77
     要
    0.77
     coerce
    0.76
     pergunta
    0.76
    POSITIVE LOGITS
     excellent
    1.72
    豊富な
    1.63
     다양한
    1.60
     versatile
    1.58
     extensive
    1.56
     multilingual
    1.56
    幅広い
    1.54
    丰富的
    1.53
     customizable
    1.52
     excelentes
    1.52
    Act Density 0.682%

    No Known Activations