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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Donna
    -0.06
     Sud
    -0.06
    Redux
    -0.06
     fro
    -0.06
    ATH
    -0.06
    ENTICATION
    -0.06
     APP
    -0.06
     DROP
    -0.06
     prohibition
    -0.06
    ATCH
    -0.06
    POSITIVE LOGITS
     drastic
    0.07
     полов
    0.07
    $search
    0.06
     jue
    0.06
    &ZeroWidthSpace
    0.06
     Nelson
    0.06
    .writeObject
    0.06
    [])↵
    0.06
    .squeeze
    0.06
     mName
    0.06
    Act Density 0.008%

    No Known Activations