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

    Neuronpedia

    INDEX
    Explanations

    URLs and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ফের
    0.54
     ArrayRef
    0.48
     colouring
    0.45
    ನ್‌
    0.45
     Coloring
    0.45
     FXR
    0.45
    𒈬
    0.44
    помним
    0.44
    ెంట్‌
    0.43
     начать
    0.42
    POSITIVE LOGITS
    illage
    0.43
    zeniu
    0.43
    emie
    0.42
    angaroo
    0.41
    gut
    0.41
    zoo
    0.41
    "
    0.40
     suburb
    0.40
    URLs
    0.40
    pected
    0.40
    Act Density 0.000%

    No Known Activations