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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uncategorized
    -0.07
    Tables
    -0.06
     Wik
    -0.06
    ่างประเทศ
    -0.06
     tourist
    -0.06
     adicion
    -0.06
     lze
    -0.06
    atore
    -0.06
     Papua
    -0.06
    ador
    -0.05
    POSITIVE LOGITS
    лон
    0.07
    ウォ
    0.07
    -parameter
    0.07
     founding
    0.06
    -fixed
    0.06
    关
    0.06
    傷
    0.06
    Ev
    0.06
    Species
    0.06
    賀
    0.06
    Act Density 0.033%

    No Known Activations