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

    Neuronpedia

    INDEX
    Explanations

    extensions, catalogs, libraries, initiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ratings
    0.81
     rating
    0.80
     renaming
    0.76
     yada
    0.74
     trying
    0.73
    スマス
    0.71
     wires
    0.71
     crying
    0.70
     Rating
    0.70
    Converting
    0.68
    POSITIVE LOGITS
     voluminous
    0.80
    locate
    0.70
     flowed
    0.67
    再度
    0.66
     maximize
    0.66
     fro
    0.65
     फॉर्म
    0.65
    textured
    0.65
     spurt
    0.65
    ách
    0.65
    Act Density 0.000%

    No Known Activations