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

    Neuronpedia

    INDEX
    Explanations

    ch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     billionaire
    -0.07
     Musik
    -0.06
    伴
    -0.06
    лагод
    -0.06
    +=(
    -0.06
     Belgian
    -0.06
    Arn
    -0.06
     Burlington
    -0.06
     implements
    -0.06
    Soup
    -0.06
    POSITIVE LOGITS
     crochet
    0.07
    TRA
    0.07
     각
    0.07
     Marines
    0.07
     DIV
    0.06
    avourites
    0.06
     NEC
    0.06
    .::.::
    0.06
    iver
    0.06
    enga
    0.06
    Act Density 0.001%

    No Known Activations