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

    Neuronpedia

    INDEX
    Explanations

    specifications and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Statement
    0.52
    Statements
    0.50
    Valid
    0.48
    -/
    0.47
    Move
    0.44
    Key
    0.44
    Gamma
    0.44
    Generator
    0.43
    valuation
    0.43
    ราะห์
    0.43
    POSITIVE LOGITS
     всі
    0.45
    져
    0.43
    אה
    0.40
     inch
    0.40
    이스
    0.39
    정도
    0.39
     uno
    0.39
     Cowboy
    0.39
    ął
    0.38
    纬
    0.38
    Act Density 0.004%

    No Known Activations