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

    Neuronpedia

    INDEX
    Explanations

    python imports and module names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xC2>
    0.45
    后
    0.39
    ρε
    0.38
     Pitt
    0.36
     Time
    0.36
     후
    0.35
     चू
    0.35
     Shields
    0.34
    後
    0.34
    囍
    0.34
    POSITIVE LOGITS
    keras
    0.46
     superconducting
    0.44
     pytest
    0.43
    evich
    0.43
    დე
    0.41
     hyperparameters
    0.39
    ندگی
    0.38
    asius
    0.37
     bosonic
    0.37
     fluxes
    0.36
    Act Density 0.000%

    No Known Activations