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

    Neuronpedia

    INDEX
    Explanations

    standard codes and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vykor
    0.49
    പരമായ
    0.47
    sthresh
    0.45
    ężczy
    0.44
    tableLayoutPanel
    0.43
    trashButton
    0.43
    केंसी
    0.42
    ؤلاء
    0.41
    ampling
    0.40
     exposureButton
    0.40
    POSITIVE LOGITS
    C
    0.54
    CP
    0.49
    B
    0.42
    G
    0.40
     dyn
    0.39
    CD
    0.38
    Q
    0.38
    ON
    0.37
    ETS
    0.36
    CS
    0.36
    Act Density 0.000%

    No Known Activations