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

    Neuronpedia

    INDEX
    Explanations

    Code/data/mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Which
    -0.07
    roph
    -0.07
     Spare
    -0.07
     gay
    -0.06
    背景
    -0.06
    IELDS
    -0.06
    oses
    -0.06
    51
    -0.06
    (place
    -0.06
     tie
    -0.06
    POSITIVE LOGITS
    _ANS
    0.07
     Journal
    0.06
    両
    0.06
    _OLD
    0.06
    /stdc
    0.06
     envision
    0.06
     재
    0.06
    	Vk
    0.06
    くれ
    0.06
    Consumer
    0.06
    Act Density 0.060%

    No Known Activations