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

    Neuronpedia

    INDEX
    Explanations

    probability of outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    0.54
    inn
    0.51
    <strong>
    0.51
    entry
    0.50
    ur
    0.48
    sin
    0.47
    ound
    0.47
    Y
    0.47
     sin
    0.46
    pre
    0.46
    POSITIVE LOGITS
     rotacao
    0.54
    hamento
    0.52
     erhöhen
    0.50
     زیرمه
    0.49
     ګرځ
    0.49
     vidhan
    0.47
     utilizamos
    0.47
     ойношот
    0.47
     jScrollPane
    0.46
    acijama
    0.46
    Act Density 0.000%

    No Known Activations