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

    Neuronpedia

    INDEX
    Explanations

    goals, problems, and eye contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.91
    ח
    0.87
    ان
    0.82
    at
    0.78
    ون
    0.78
    на
    0.77
    د
    0.75
    ק
    0.75
    اب
    0.74
    in
    0.73
    POSITIVE LOGITS
    ↵↵
    0.68
    -
    0.67
     Öncelikle
    0.63
    У
    0.57
    ，
    0.56
    ありますが
    0.55
    )，
    0.55
    ),
    0.54
    },
    0.54
    Α
    0.52
    Act Density 0.425%

    No Known Activations