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

    Neuronpedia

    INDEX
    Explanations

    errors='ignore'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьев
    1.84
    incón
    1.78
    த்
    1.77
    Σ
    1.76
    דם
    1.74
    籲
    1.74
    યુ
    1.74
     Elevations
    1.73
     monotone
    1.73
    UAGES
    1.71
    POSITIVE LOGITS
    u
    1.67
    óloga
    1.52
    can
    1.49
    ه
    1.47
    ci
    1.40
    里的
    1.39
    TES
    1.36
     hate
    1.34
    yaml
    1.34
    会有
    1.32
    Act Density 0.002%

    No Known Activations