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

    Neuronpedia

    INDEX
    Explanations

    missions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rochester
    -0.07
    ню
    -0.07
     translations
    -0.07
    rava
    -0.06
    nP
    -0.06
     celebrations
    -0.06
     що
    -0.06
     workbook
    -0.06
    Как
    -0.06
     правда
    -0.06
    POSITIVE LOGITS
     sendMessage
    0.06
    扣
    0.06
    _possible
    0.06
     endIndex
    0.06
    ुछ
    0.06
    *L
    0.06
    _nd
    0.06
    _PAUSE
    0.06
    OrNull
    0.06
    :c
    0.06
    Act Density 0.009%

    No Known Activations