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

    Neuronpedia

    INDEX
    Explanations

    Randomness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     machining
    -0.09
     Tel
    -0.08
     Plugin
    -0.08
     tel
    -0.08
    ↵//
    -0.07
     Telescope
    -0.07
    observe
    -0.07
     trabajos
    -0.07
     wasting
    -0.07
     molding
    -0.07
    POSITIVE LOGITS
     depending
    0.11
    Depending
    0.10
    depending
    0.10
     dependendo
    0.10
     dependiendo
    0.09
     afh
    0.09
     الحجم
    0.09
    字
    0.09
    Тип
    0.08
    ിധ
    0.08
    Act Density 0.243%

    No Known Activations