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

    Neuronpedia

    INDEX
    Explanations

    specific technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    COMMENT
    0.43
    iyah
    0.43
     énon
    0.42
     Immun
    0.42
     wenig
    0.42
     schn
    0.41
    zellen
    0.40
    mio
    0.40
    tedir
    0.40
    ုပ်
    0.39
    POSITIVE LOGITS
     oxalic
    0.48
    のため
    0.48
     extravagance
    0.46
    ри
    0.45
     disebabkan
    0.45
     robbing
    0.44
     vadanti
    0.43
     fullness
    0.43
     অতঃপর
    0.42
     kq
    0.42
    Act Density 0.000%

    No Known Activations