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

    Neuronpedia

    INDEX
    Explanations

    arranged

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rule
    -0.07
    spr
    -0.06
     "^
    -0.06
    _abort
    -0.06
     hasn
    -0.06
    reat
    -0.06
     may
    -0.06
    _x
    -0.06
    Aspect
    -0.06
    _guest
    -0.06
    POSITIVE LOGITS
     Eig
    0.06
    ije
    0.06
     počíta
    0.06
     yönetimi
    0.06
     českých
    0.06
     bulunur
    0.06
     Quy
    0.06
    razione
    0.06
     nebylo
    0.06
     Ric
    0.06
    Act Density 0.041%

    No Known Activations