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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.06
    　
    -0.06
    upload
    -0.06
    _user
    -0.06
     insurg
    -0.06
     Zucker
    -0.06
    ۱۴
    -0.06
    etu
    -0.06
     економ
    -0.06
    _NORMAL
    -0.06
    POSITIVE LOGITS
     faction
    0.08
     sequence
    0.07
     went
    0.07
     tady
    0.06
     LOAD
    0.06
    thed
    0.06
     FC
    0.06
     realistically
    0.06
    incipal
    0.06
    =log
    0.06
    Act Density 0.065%

    No Known Activations