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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Favorite
    -0.07
     filmm
    -0.07
    ember
    -0.07
     Rounded
    -0.06
    äft
    -0.06
    .STRING
    -0.06
    Human
    -0.06
    .GetData
    -0.06
     mortgages
    -0.06
     William
    -0.06
    POSITIVE LOGITS
    а
    0.07
     attenu
    0.07
     χα
    0.07
     si
    0.06
     elle
    0.06
    (s
    0.06
    _ylabel
    0.06
    adjust
    0.06
     squir
    0.06
    lj
    0.06
    Act Density 0.132%

    No Known Activations