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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     three
    -0.08
    二十年
    -0.07
    *self
    -0.07
     twice
    -0.07
     eight
    -0.07
    QUIRED
    -0.07
    _widget
    -0.07
    (grad
    -0.07
    alph
    -0.07
     curses
    -0.07
    POSITIVE LOGITS
    放开
    0.07
    ⊦
    0.07
     sabe
    0.07
    开了
    0.07
    SpecWarn
    0.06
    إصلاح
    0.06
    💥
    0.06
     gł
    0.06
    	esc
    0.06
     establishment
    0.06
    Act Density 0.033%

    No Known Activations