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

    Neuronpedia

    INDEX
    Explanations

    ######

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ->↵
    -0.08
     poi
    -0.06
    ()));↵
    -0.06
     Surrey
    -0.06
    booking
    -0.06
     VC
    -0.06
    Enterprise
    -0.06
     सब
    -0.06
     Covent
    -0.06
     Wrestling
    -0.06
    POSITIVE LOGITS
     vandalism
    0.07
    ailure
    0.06
     société
    0.06
     legislation
    0.06
     bestowed
    0.06
    งศ
    0.06
    valuator
    0.06
     يك
    0.06
     Farrell
    0.06
    胸
    0.06
    Act Density 0.000%

    No Known Activations