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

    Neuronpedia

    INDEX
    Explanations

    :name

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probabilities
    -0.07
     dimensions
    -0.06
     bằng
    -0.06
     Elon
    -0.06
     sơ
    -0.06
     cotton
    -0.06
     Atlantis
    -0.06
    =explode
    -0.06
     elastic
    -0.06
     hr
    -0.06
    POSITIVE LOGITS
    getSource
    0.06
    io
    0.06
    ebiliriz
    0.06
    .getField
    0.06
    ्क
    0.06
     terug
    0.06
    -O
    0.06
    >All
    0.06
    _SCOPE
    0.06
    venge
    0.06
    Act Density 0.001%

    No Known Activations