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

    Neuronpedia

    INDEX
    Explanations

    dice translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    問題を
    0.49
    ್ಯೂ
    0.46
     qubit
    0.45
     Detect
    0.44
    ieving
    0.44
     madde
    0.44
    LER
    0.43
     auxilia
    0.43
     империи
    0.43
    кус
    0.42
    POSITIVE LOGITS
     rupees
    0.42
    Saturday
    0.41
    Thursday
    0.41
     ½
    0.40
    loans
    0.40
     didn
    0.39
    she
    0.39
     browns
    0.39
    selling
    0.39
     shillings
    0.38
    Act Density 0.000%

    No Known Activations