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

    Neuronpedia

    INDEX
    Explanations

    request

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     युवक
    0.80
     Cond
    0.79
    Cond
    0.71
    ?',
    0.71
     War
    0.66
     માણ
    0.66
     laws
    0.65
    cond
    0.65
     germ
    0.64
    ?),
    0.63
    POSITIVE LOGITS
    chets
    0.76
    attoo
    0.73
    prints
    0.73
    irons
    0.71
     маг
    0.71
     Ecusson
    0.69
    Gets
    0.67
    republik
    0.67
    رياض
    0.67
    爬
    0.66
    Act Density 0.001%

    No Known Activations