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

    Neuronpedia

    INDEX
    Explanations

    logging and code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elution
    0.46
     estruturas
    0.41
     orb
    0.40
     enzymes
    0.39
     kiosks
    0.39
     Enzymes
    0.38
     kic
    0.38
    પુ
    0.38
     nests
    0.37
     conco
    0.37
    POSITIVE LOGITS
    ù
    0.44
    šte
    0.42
    суль
    0.42
    🔛
    0.41
    atien
    0.41
    訢
    0.40
     開始
    0.39
    ̀
    0.39
    𝐂
    0.39
    🔙
    0.39
    Act Density 0.001%

    No Known Activations