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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spree
    -0.07
     peaceful
    -0.06
    チュ
    -0.06
     PDO
    -0.06
     succ
    -0.06
     Irvine
    -0.06
     střední
    -0.06
     แล
    -0.06
     множе
    -0.06
     Kurds
    -0.06
    POSITIVE LOGITS
     tom
    0.07
     Girlfriend
    0.06
     %@
    0.06
     Potion
    0.06
     aliqua
    0.06
     contag
    0.06
    (Image
    0.06
     guit
    0.06
     Cardio
    0.06
    lename
    0.06
    Act Density 0.035%

    No Known Activations