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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clone
    -0.08
     何
    -0.07
    collect
    -0.06
    Glyph
    -0.06
    晓
    -0.06
    }}↵↵
    -0.06
    Cleaning
    -0.06
     culinary
    -0.06
    чет
    -0.06
    _checkout
    -0.06
    POSITIVE LOGITS
    سل
    0.07
    :X
    0.06
    razione
    0.06
    stanov
    0.06
    ko
    0.06
     questa
    0.06
     hair
    0.06
     Chad
    0.06
    ाभ
    0.06
     renderItem
    0.06
    Act Density 0.040%

    No Known Activations