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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distract
    -0.07
     nurt
    -0.07
     услов
    -0.07
    ока
    -0.07
    ков
    -0.06
     Regulation
    -0.06
    ubar
    -0.06
    ForMember
    -0.06
    елов
    -0.06
    Exit
    -0.06
    POSITIVE LOGITS
    =context
    0.07
     ragazzi
    0.06
     دستگاه
    0.06
    ('*
    0.06
     MASTER
    0.06
    _IEnumerator
    0.06
     může
    0.06
    'nda
    0.06
    POP
    0.05
    کس
    0.05
    Act Density 0.027%

    No Known Activations