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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     líder
    -0.07
     shooters
    -0.07
    โรงเร
    -0.07
    _grade
    -0.07
     interruptions
    -0.07
     decorating
    -0.07
    oden
    -0.06
    IDEO
    -0.06
    ける
    -0.06
     İng
    -0.06
    POSITIVE LOGITS
     Ф
    0.06
    板
    0.06
    .dll
    0.06
     Bool
    0.06
    ×↵↵
    0.06
    _Syntax
    0.06
     postfix
    0.06
    .%
    0.06
     equity
    0.06
    िश
    0.06
    Act Density 0.005%

    No Known Activations