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

    Neuronpedia

    INDEX
    Explanations

    text formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gran
    -0.07
     search
    -0.07
     pipeline
    -0.07
     glyph
    -0.07
    _factor
    -0.07
     Nutrition
    -0.07
    compat
    -0.07
     insects
    -0.06
     puls
    -0.06
     Trust
    -0.06
    POSITIVE LOGITS
     Sov
    0.06
     свои
    0.06
    oir
    0.06
     bulunuyor
    0.06
    就
    0.06
    �
    0.06
     доп
    0.06
     passe
    0.06
    揮
    0.06
     çay
    0.06
    Act Density 0.013%

    No Known Activations