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

    Neuronpedia

    INDEX
    Explanations

    Hyphens/Ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uters
    -0.07
    ']=='
    -0.06
    앙
    -0.06
     :]↵
    -0.06
    Reality
    -0.06
    _observer
    -0.06
    الب
    -0.06
    educ
    -0.06
    matcher
    -0.06
    _checks
    -0.06
    POSITIVE LOGITS
     deport
    0.07
     قهر
    0.07
     plantation
    0.07
     Чем
    0.06
     Carlton
    0.06
     paving
    0.06
    .slf
    0.06
    utta
    0.06
     wirk
    0.06
     insulting
    0.06
    Act Density 0.034%

    No Known Activations