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

    Neuronpedia

    INDEX
    Explanations

    uble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ट
    -0.07
    バス
    -0.07
     Τζ
    -0.06
     приход
    -0.06
     Після
    -0.06
    .press
    -0.06
    本当
    -0.06
    regnum
    -0.06
    庄
    -0.06
     thiểu
    -0.06
    POSITIVE LOGITS
     soluble
    0.13
    uble
    0.08
     dialogue
    0.07
    otch
    0.07
     occult
    0.06
    ante
    0.06
     SIMPLE
    0.06
     dumb
    0.06
     mitochond
    0.06
     REPL
    0.06
    Act Density 0.003%

    No Known Activations