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

    Neuronpedia

    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     powerful
    -0.06
     ["
    -0.06
     translating
    -0.06
     Gef
    -0.06
     Bulk
    -0.06
    .$
    -0.06
    ائلة
    -0.06
    .filtered
    -0.06
     wast
    -0.06
    敬
    -0.06
    POSITIVE LOGITS
     ssize
    0.06
     hello
    0.06
     складі
    0.06
    jian
    0.06
     takip
    0.06
     плеч
    0.06
    (?
    0.06
     benign
    0.06
    554
    0.06
    Execution
    0.06
    Act Density 0.009%

    No Known Activations