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

    Neuronpedia

    INDEX
    Explanations

    questions and informational statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toolbox
    0.34
     strategies
    0.34
     alphabet
    0.33
     accuracies
    0.33
    strategies
    0.33
    ibilidades
    0.33
     ejército
    0.32
     Aragón
    0.32
    scaler
    0.32
     کہ
    0.30
    POSITIVE LOGITS
    לב
    0.33
     Einwilligung
    0.32
    חו
    0.32
    များသည်
    0.32
    犃
    0.32
     деца
    0.32
     জ্বাল
    0.31
    Benzoimidazol
    0.31
    lcii
    0.31
    妻子
    0.30
    Act Density 0.001%

    No Known Activations