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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cavern
    -0.07
     Weaver
    -0.06
    好了
    -0.06
    .WRAP
    -0.06
     Θεσσα
    -0.06
    Painter
    -0.06
     لح
    -0.06
     zien
    -0.06
    eve
    -0.06
     서로
    -0.06
    POSITIVE LOGITS
     INCLUDING
    0.08
    .posts
    0.07
     bottom
    0.06
     consultation
    0.06
    _BOX
    0.06
     */,↵
    0.06
     obl
    0.06
     placed
    0.06
    	dataType
    0.06
     adult
    0.06
    Act Density 0.010%

    No Known Activations