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

    Neuronpedia

    INDEX
    Explanations

    self-help advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ([]
    -0.07
    ʇ
    -0.07
    (actual
    -0.07
    今回は
    -0.07
     mãe
    -0.06
    (){}↵
    -0.06
    🐸
    -0.06
    今回の
    -0.06
    ansen
    -0.06
     ()
↵
    -0.06
    POSITIVE LOGITS
    INC
    0.07
    Bomb
    0.06
    عق
    0.06
    雍
    0.06
    XXXXXXXX
    0.06
    LEAN
    0.06
     conduc
    0.06
    对标
    0.06
     emblem
    0.06
     Highlander
    0.06
    Act Density 0.082%

    No Known Activations