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

    Neuronpedia

    INDEX
    Explanations

    found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marathon
    -0.06
    eroon
    -0.06
     molt
    -0.06
    UTH
    -0.06
     růz
    -0.06
    大學
    -0.06
    LOOR
    -0.06
    鐘
    -0.06
    Jackson
    -0.05
    -air
    -0.05
    POSITIVE LOGITS
    .port
    0.08
     QFile
    0.07
    .element
    0.06
     Batı
    0.06
     Sharing
    0.06
    .cross
    0.06
     отк
    0.06
    dh
    0.06
     edin
    0.06
    fony
    0.06
    Act Density 0.014%

    No Known Activations