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

    Neuronpedia

    INDEX
    Explanations

    weight units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Completion
    -0.08
     也
    -0.08
    Decode
    -0.07
     ситуа
    -0.07
     Height
    -0.06
     Prefix
    -0.06
     içine
    -0.06
    ेखत
    -0.06
    گار
    -0.06
     flush
    -0.06
    POSITIVE LOGITS
    ’’
    0.07
    $title
    0.06
    ）（
    0.06
    .if
    0.06
    ';↵↵
    0.06
     المش
    0.06
    ’all
    0.06
     ド
    0.06
    -commerce
    0.06
     kilograms
    0.06
    Act Density 0.017%

    No Known Activations