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

    Neuronpedia

    INDEX
    Explanations

    imports and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ezekiel
    0.43
    ენტი
    0.41
     GS
    0.39
     الجديد
    0.39
     singers
    0.37
    Combine
    0.37
    ופי
    0.37
     unifying
    0.37
     individual
    0.37
     juu
    0.37
    POSITIVE LOGITS
     pericol
    0.45
    vres
    0.43
     অস্ব
    0.40
     নিত্য
    0.39
     Metadata
    0.39
     memory
    0.38
     Meta
    0.38
     memoria
    0.38
     memória
    0.37
    Meta
    0.37
    Act Density 0.000%

    No Known Activations