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

    Neuronpedia

    INDEX
    Explanations

    referring to previous items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     საშუალ
    0.52
    áním
    0.49
    ľov
    0.47
    atres
    0.47
     başladı
    0.46
     dzī
    0.45
     zdol
    0.45
    atsiooni
    0.45
     capacités
    0.45
    année
    0.45
    POSITIVE LOGITS
     which
    0.82
     aforementioned
    0.75
     diese
    0.66
     these
    0.66
     respectively
    0.63
     thine
    0.63
     autoch
    0.63
     dieser
    0.62
     hers
    0.62
     respective
    0.60
    Act Density 0.000%

    No Known Activations