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

    Neuronpedia

    INDEX
    Explanations

    explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.44
    9
    0.43
    4
    0.37
    6
    0.36
    8
    0.36
    ON
    0.33
    AN
    0.32
    тор
    0.31
    RAY
    0.30
    ிக்
    0.30
    POSITIVE LOGITS
     the
    0.36
    ו
    0.33
    و
    0.32
     sedentary
    0.30
    iin
    0.29
    想到
    0.29
     Canadi
    0.29
     explanations
    0.28
     Hokkaido
    0.28
    די
    0.28
    Act Density 0.090%

    No Known Activations