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

    Neuronpedia

    INDEX
    Explanations

    technical items

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    পা
    0.59
    셍
    0.55
    워
    0.55
    සු
    0.54
     школовања
    0.54
     carriages
    0.54
     ஹி
    0.53
    入荷
    0.53
    🇵
    0.52
     populations
    0.52
    POSITIVE LOGITS
     Connector
    0.68
     گردد
    0.60
     TSE
    0.57
     connector
    0.56
     fluxo
    0.55
     Reader
    0.55
     Voter
    0.55
    connector
    0.55
     Inn
    0.54
    ιάς
    0.53
    Act Density 0.000%

    No Known Activations