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

    Neuronpedia

    INDEX
    Explanations

    technical terms and affiliations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overcrow
    0.50
    "]),
    0.46
     escolares
    0.45
     pai
    0.44
    ့်
    0.44
    )
    0.44
    :
    0.43
    ;
    0.43
     ನಾಲ್
    0.42
     nail
    0.42
    POSITIVE LOGITS
    зи
    0.57
    ến
    0.49
     conexión
    0.49
     kiếm
    0.44
    з
    0.44
    ặc
    0.43
    ен
    0.43
    ро
    0.43
    itas
    0.43
    बंध
    0.42
    Act Density 0.005%

    No Known Activations