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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாதார
    0.40
     scanty
    0.39
     periodicity
    0.38
    gameField
    0.38
     pozosta
    0.36
     synonym
    0.36
     fragmentary
    0.36
     elucid
    0.35
     grotesque
    0.34
     insoluble
    0.34
    POSITIVE LOGITS
    6
    0.44
    8
    0.43
    4
    0.41
    2
    0.39
    7
    0.38
    INA
    0.36
    9
    0.35
    وو
    0.34
    <strong>
    0.34
    mj
    0.34
    Act Density 0.004%

    No Known Activations