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

    Neuronpedia

    INDEX
    Explanations

    invalid email addresses or operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ‎
    0.46
     ગો
    0.42
    ゴ
    0.41
    対
    0.40
     》
    0.40
    IDADE
    0.40
    ‎
    0.40
     ヨ
    0.38
     acting
    0.38
    راف
    0.37
    POSITIVE LOGITS
     Invalid
    0.54
     inval
    0.48
     invalid
    0.47
     invál
    0.46
    ressant
    0.46
    invalid
    0.45
    Invalid
    0.45
    եռ
    0.43
     Retry
    0.42
    valids
    0.42
    Act Density 0.000%

    No Known Activations