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

    Neuronpedia

    INDEX
    Explanations

    numbers and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Since
    0.33
    src
    0.31
    variant
    0.31
    from
    0.29
    msg
    0.29
    Errors
    0.28
    From
    0.28
    before
    0.28
    eaa
    0.27
    Msg
    0.27
    POSITIVE LOGITS
     química
    0.31
     hükü
    0.29
     çöze
    0.28
     ڈپاز
    0.28
     पाउडर
    0.28
     Química
    0.28
     prende
    0.28
     químico
    0.28
     aujourd
    0.27
     Joaqu
    0.27
    Act Density 0.000%

    No Known Activations