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

    Neuronpedia

    INDEX
    Explanations

    technical domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anken
    0.93
    円以上
    0.91
    름
    0.90
    ringar
    0.89
     esquema
    0.88
    вета
    0.87
    beelding
    0.83
    espo
    0.82
    lapse
    0.81
     acquittal
    0.81
    POSITIVE LOGITS
     Pitts
    1.60
    istika
    1.60
    ist
    1.55
    istically
    1.53
    ists
    1.47
    ization
    1.47
     Oviedo
    1.46
    ism
    1.46
    ificance
    1.44
     Ols
    1.43
    Act Density 0.512%

    No Known Activations