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

    Neuronpedia

    INDEX
    Explanations

    programming libraries

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mat
    0.69
    랙
    0.66
    জার
    0.65
    )]
    0.64
    зя
    0.63
     esigen
    0.62
     AFFA
    0.62
    evin
    0.62
    ार्
    0.60
    Soul
    0.59
    POSITIVE LOGITS
     udara
    0.62
     california
    0.60
    eton
    0.59
     segar
    0.59
    ահ
    0.59
     OCR
    0.58
    lowski
    0.58
    instellungen
    0.58
     decorative
    0.57
     Informationen
    0.57
    Act Density 0.008%

    No Known Activations