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

    Neuronpedia

    INDEX
    Explanations

    is there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dostępne
    1.15
     you
    1.03
     vorhanden
    1.03
    pires
    1.00
     expiresIn
    0.98
     resonances
    0.97
     ஏற்படும்
    0.97
     bestehen
    0.96
     denoted
    0.96
     devils
    0.95
    POSITIVE LOGITS
    й
    0.89
    пример
    0.84
    는
    0.78
    rnd
    0.78
     pregunt
    0.75
    ने
    0.74
     सवाल
    0.72
    की
    0.72
    خانه
    0.71
    मा
    0.71
    Act Density 0.032%

    No Known Activations