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

    Neuronpedia

    INDEX
    Explanations

    Code or data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hé
    -0.07
     trä
    -0.07
    _blue
    -0.06
    ाप
    -0.06
     vidé
    -0.06
    037
    -0.06
    azole
    -0.06
     FLAG
    -0.06
    .unit
    -0.06
    ió
    -0.06
    POSITIVE LOGITS
    матрива
    0.07
     Initi
    0.07
     All
    0.06
    []){↵
    0.06
     LS
    0.06
     anc
    0.06
     пись
    0.06
    oss
    0.06
    (${
    0.06
     decency
    0.06
    Act Density 0.001%

    No Known Activations