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

    Neuronpedia

    INDEX
    Explanations

    formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _erase
    -0.08
    ैय
    -0.07
     downright
    -0.07
     Salv
    -0.07
     expansions
    -0.07
     Jump
    -0.07
     Else
    -0.06
     pills
    -0.06
     framerate
    -0.06
     Way
    -0.06
    POSITIVE LOGITS
     예정
    0.06
    ontent
    0.06
     '%"
    0.06
    тех
    0.06
     Guinea
    0.05
     unrealistic
    0.05
     σαν
    0.05
    orio
    0.05
    ΟΥΣ
    0.05
    \Entities
    0.05
    Act Density 0.099%

    No Known Activations