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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    很
    -0.07
    "How
    -0.07
    endpoint
    -0.06
     blogging
    -0.06
     pregnant
    -0.06
    ังก
    -0.06
    $tmp
    -0.06
     encontr
    -0.06
     же
    -0.06
    addGap
    -0.06
    POSITIVE LOGITS
    .Flag
    0.07
    钮
    0.07
     Exercises
    0.07
    ByName
    0.06
     کنیم
    0.06
     Tonight
    0.06
     decals
    0.06
    .resp
    0.06
     sowie
    0.06
     paj
    0.06
    Act Density 0.093%

    No Known Activations