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

    Neuronpedia

    INDEX
    Explanations

    Base conversions/math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Legacy
    -0.06
     deadly
    -0.06
     Rising
    -0.06
     Communities
    -0.06
     degrees
    -0.06
     verdade
    -0.06
     IGNORE
    -0.06
     Kak
    -0.06
     Bunny
    -0.05
    ..↵↵
    -0.05
    POSITIVE LOGITS
    UIView
    0.07
    government
    0.06
    Categories
    0.06
    İng
    0.06
    .const
    0.06
    Posted
    0.06
    中文字幕
    0.06
    電視
    0.06
     fucked
    0.06
    _primitive
    0.06
    Act Density 0.005%

    No Known Activations