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

    Neuronpedia

    INDEX
    Explanations

    ad or innov

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anterie
    0.41
     Ronnie
    0.40
     nghiêm
    0.39
    Ukraine
    0.39
    ഒ
    0.39
    oglobine
    0.38
    wallepics
    0.38
     natthi
    0.38
    striction
    0.38
    itchie
    0.37
    POSITIVE LOGITS
    ador
    2.02
    ADOR
    1.77
    adors
    1.62
    adores
    1.60
    adora
    1.55
    adoras
    1.53
     dor
    1.43
    dor
    1.41
    adore
    1.36
    idor
    1.34
    Act Density 0.006%

    No Known Activations