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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'B
    -0.08
     Met
    -0.07
    ्‍
    -0.07
    _work
    -0.06
    ्म
    -0.06
    嗎
    -0.06
    Ray
    -0.06
    Met
    -0.06
     Nếu
    -0.06
    .Web
    -0.06
    POSITIVE LOGITS
     tus
    0.06
     ніч
    0.06
    sgi
    0.06
     cite
    0.06
    ================
    0.06
     galaxies
    0.06
     pus
    0.06
     pathetic
    0.06
    orca
    0.06
     suche
    0.06
    Act Density 0.115%

    No Known Activations