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

    Neuronpedia

    INDEX
    Explanations

    numpy and APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entropy
    0.43
    敗
    0.42
     Entropy
    0.41
     Photon
    0.40
    戦闘
    0.39
    ЛИ
    0.39
    不明
    0.38
     व्याकरण
    0.38
     Calle
    0.38
    படி
    0.37
    POSITIVE LOGITS
    amps
    0.42
     Mol
    0.40
     amplifiers
    0.40
    ográficos
    0.40
    acious
    0.38
     Amp
    0.38
    Mol
    0.38
    Amp
    0.38
    ained
    0.37
    rade
    0.36
    Act Density 0.000%

    No Known Activations