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

    Neuronpedia

    INDEX
    Explanations

    effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andre
    -0.07
     CSV
    -0.07
     가지고
    -0.07
     מספיק
    -0.07
     danh
    -0.07
    如下
    -0.07
    ="../../../
    -0.07
    stash
    -0.07
     "../../../../
    -0.07
    stąpi
    -0.07
    POSITIVE LOGITS
     effects
    0.11
     effect
    0.10
     Effects
    0.09
     Effect
    0.08
     энер
    0.08
    .prob
    0.08
    	effect
    0.08
    -effect
    0.07
     sẽ
    0.07
     ESA
    0.07
    Act Density 0.071%

    No Known Activations