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

    Neuronpedia

    INDEX
    Explanations

    relationships, affairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weighs
    -0.06
    는지
    -0.06
    sse
    -0.06
    ouncements
    -0.06
    zing
    -0.06
     airing
    -0.06
     minh
    -0.06
    pga
    -0.06
    imbus
    -0.06
    mesine
    -0.06
    POSITIVE LOGITS
    ...\
    0.06
    #\
    0.06
    _trip
    0.06
    -widget
    0.06
    Pack
    0.06
     Daniels
    0.06
    exam
    0.06
     representation
    0.06
     sc
    0.06
    EDI
    0.06
    Act Density 0.025%

    No Known Activations