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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aldi
    -0.07
    ifar
    -0.07
    ucz
    -0.06
    oglob
    -0.06
    éľ
    -0.06
    aylight
    -0.06
    entric
    -0.06
    ray
    -0.06
     Gust
    -0.06
    sburg
    -0.06
    POSITIVE LOGITS
    LS
    0.06
    407
    0.06
    ibus
    0.06
    ym
    0.06
    steder
    0.06
    åIJ
    0.06
    bjerg
    0.06
    ets
    0.06
     Rolling
    0.06
     synthesis
    0.06
    Act Density 0.090%

    No Known Activations