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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hinted
    -0.08
     ironically
    -0.08
     laugh
    -0.08
     influences
    -0.07
     existen
    -0.07
    identified
    -0.07
     finalist
    -0.07
    Than
    -0.07
     identify
    -0.07
     hymn
    -0.07
    POSITIVE LOGITS
     Immigration
    0.09
     ذهب
    0.08
    .iteritems
    0.08
     пада
    0.08
     כיצד
    0.07
     immigration
    0.07
    els
    0.07
    _ascii
    0.07
     બત
    0.07
     ataque
    0.07
    Act Density 0.020%

    No Known Activations