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

    Neuronpedia

    INDEX
    Explanations

    TODO comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MaxIntensity
    0.50
    Eden
    0.41
     stepfather
    0.41
     लह
    0.40
     krwi
    0.38
    ὦ
    0.38
    doctorId
    0.37
    тура
    0.37
    Freight
    0.36
    Sulf
    0.36
    POSITIVE LOGITS
     Auto
    1.02
    Auto
    0.88
    auto
    0.87
     auto
    0.85
     TODO
    0.79
     자동
    0.70
     自動
    0.69
     AUTO
    0.68
    自动
    0.67
    AUTO
    0.63
    Act Density 0.000%

    No Known Activations