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

    Neuronpedia

    INDEX
    Explanations

    apoptosis, soccer, victory, strftime, solution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     menilai
    0.47
     mlij
    0.46
    ਣਾ
    0.44
    W
    0.44
    Xa
    0.43
     conveniente
    0.42
    ਈ
    0.42
     ACHIEVEMENT
    0.42
    恢復
    0.42
     രാവിലെ
    0.42
    POSITIVE LOGITS
    cans
    0.50
    th
    0.47
    otics
    0.46
    te
    0.45
    isca
    0.45
    c
    0.45
     offseason
    0.44
    the
    0.44
    dies
    0.44
    ೋಗ್ಯ
    0.43
    Act Density 0.000%

    No Known Activations