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

    Neuronpedia

    INDEX
    Explanations

    mechanical movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heated
    -0.07
    information
    -0.07
    NAS
    -0.07
    йом
    -0.06
     vocabulary
    -0.06
     onder
    -0.06
    (IO
    -0.06
    Keith
    -0.06
     tro
    -0.06
     probabilities
    -0.06
    POSITIVE LOGITS
    िफ
    0.06
    되어
    0.06
    ็กซ
    0.06
     CGContext
    0.06
     topology
    0.06
     congrat
    0.06
    783
    0.06
     holy
    0.06
    expr
    0.06
    泥
    0.06
    Act Density 0.056%

    No Known Activations