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

    Neuronpedia

    INDEX
    Explanations

    custom templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    physical
    0.45
    DIO
    0.44
    7
    0.44
    lambda
    0.44
     fisica
    0.44
     Sait
    0.43
     Vee
    0.42
    5
    0.42
    gum
    0.42
     Ohio
    0.42
    POSITIVE LOGITS
    動画
    0.51
    mandu
    0.47
     動画
    0.47
    れます
    0.46
    鮮
    0.45
    izia
    0.45
     Michelangelo
    0.45
     Sentencing
    0.45
     vidéos
    0.44
     shrug
    0.44
    Act Density 0.002%

    No Known Activations