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

    Neuronpedia

    INDEX
    Explanations

    labels followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     piso
    0.45
    式の
    0.42
     formula
    0.42
    姶
    0.41
     hunting
    0.41
     fórmula
    0.41
     floors
    0.41
     mastering
    0.41
    槊
    0.41
     केंद
    0.40
    POSITIVE LOGITS
    ’),
    0.48
     የታ
    0.46
    adden
    0.42
     mesela
    0.42
    >,
    0.42
    cH
    0.41
     tabii
    0.41
    content
    0.40
    '(
    0.40
    Overlay
    0.40
    Act Density 0.000%

    No Known Activations