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

    Neuronpedia

    INDEX
    Explanations

    long and short descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বসাইট
    1.01
    ب
    0.96
    많
    0.93
    да
    0.92
    ación
    0.91
    ment
    0.89
    いた
    0.89
    ata
    0.88
     \%
    0.87
    ov
    0.85
    POSITIVE LOGITS
    e
    1.31
    ン
    1.22
    יה
    1.19
    ه
    1.17
    يت
    1.16
    }}
    1.13
    ิ
    1.13
    ो
    1.13
    instagood
    1.12
    ה
    1.12
    Act Density 0.110%

    No Known Activations