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

    Neuronpedia

    INDEX
    Explanations

    locations and directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /background
    -0.07
    대비
    -0.07
     herd
    -0.07
    _Path
    -0.07
     invaded
    -0.06
    _MUX
    -0.06
    according
    -0.06
     mourn
    -0.06
    邦
    -0.06
    户
    -0.06
    POSITIVE LOGITS
     audi
    0.06
    244
    0.06
    enze
    0.06
    рон
    0.06
    99
    0.06
    linky
    0.06
     magician
    0.06
     nom
    0.06
     filler
    0.06
     dří
    0.06
    Act Density 0.208%

    No Known Activations