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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    居民
    -0.06
    vání
    -0.06
     doporuč
    -0.06
    _selection
    -0.06
     karena
    -0.06
     ashes
    -0.06
    dığında
    -0.06
    ườn
    -0.06
    GPC
    -0.06
     organizer
    -0.06
    POSITIVE LOGITS
    only
    0.07
     удов
    0.07
    QRST
    0.07
     적용
    0.07
    /signup
    0.07
     Staff
    0.07
     slice
    0.06
    >".
    0.06
     colorWithRed
    0.06
     Petsc
    0.06
    Act Density 0.075%

    No Known Activations