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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eigentlich
    -0.07
    /">
    -0.07
    ुबह
    -0.06
     تأ
    -0.06
    *h
    -0.06
    LEE
    -0.06
    ennie
    -0.06
     강
    -0.06
    *\
    -0.06
     clumsy
    -0.06
    POSITIVE LOGITS
     digitally
    0.07
    Reference
    0.06
    _resolution
    0.06
    ารณ
    0.06
     strategic
    0.06
    znam
    0.06
     resid
    0.06
    refs
    0.06
     Digital
    0.06
    .disconnect
    0.06
    Act Density 0.006%

    No Known Activations