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

    Neuronpedia

    INDEX
    Explanations

    Ascendant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assets
    -0.10
     Assets
    -0.09
     wir
    -0.09
    _assets
    -0.08
    'n
    -0.08
    των
    -0.08
     machinery
    -0.07
     ich
    -0.07
     iterable
    -0.07
     multiline
    -0.07
    POSITIVE LOGITS
     impressão
    0.09
     Impression
    0.09
     impressions
    0.08
     hơi
    0.08
     ори
    0.08
     steep
    0.08
    ೀಯ
    0.08
    _orientation
    0.08
     वो
    0.08
    Им
    0.08
    Act Density 0.001%

    No Known Activations