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

    Neuronpedia

    INDEX
    Explanations

    punctuation and common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edit
    -0.07
    inkle
    -0.06
     suspicion
    -0.06
    Pokud
    -0.06
    円
    -0.06
     modes
    -0.06
     tones
    -0.06
    //↵
    -0.06
    ..."↵↵
    -0.06
    licant
    -0.06
    POSITIVE LOGITS
     vur
    0.07
     몽
    0.07
     Ear
    0.06
    кус
    0.06
     ат
    0.06
    [group
    0.06
     Vit
    0.06
     $"{
    0.06
     khác
    0.06
     tah
    0.06
    Act Density 0.027%

    No Known Activations