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

    Neuronpedia

    INDEX
    Explanations

    anime and platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }-
    0.52
     डिस्क्रिप्शन
    0.46
    agonal
    0.46
    ರದ
    0.45
    但在
    0.45
    osomal
    0.44
    হইল
    0.44
     因为
    0.43
    obili
    0.43
    但是在
    0.43
    POSITIVE LOGITS
     buckles
    0.49
     сервис
    0.44
     service
    0.44
     VC
    0.43
     misconduct
    0.42
     FIFA
    0.42
     dishonesty
    0.42
     commerce
    0.42
     reputation
    0.41
     monsoon
    0.41
    Act Density 0.021%

    No Known Activations