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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َو
    -0.07
    lessness
    -0.07
    	Service
    -0.06
    mony
    -0.06
     зменш
    -0.06
    าณาจ
    -0.06
    .symmetric
    -0.06
    outines
    -0.06
    。「
    -0.06
     曰
    -0.06
    POSITIVE LOGITS
    アル
    0.07
    _multiplier
    0.07
     ferv
    0.07
    OKIE
    0.07
    'al
    0.06
    /comments
    0.06
    iyor
    0.06
     tř
    0.06
    |.↵
    0.06
    До
    0.06
    Act Density 0.133%

    No Known Activations