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

    Neuronpedia

    INDEX
    Explanations

    email subjects and templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Х
    0.59
    X
    0.59
    b
    0.53
    т
    0.53
    ц
    0.53
    е
    0.49
    ч
    0.49
    em
    0.49
    р
    0.49
    з
    0.48
    POSITIVE LOGITS
     espécies
    0.38
     errorCode
    0.38
     coû
    0.38
     émer
    0.38
     personnelle
    0.38
    πουργ
    0.38
     ومت
    0.38
    жели
    0.37
    中でも
    0.37
    <>();
    0.36
    Act Density 0.004%

    No Known Activations