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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paed
    -0.06
     Atkins
    -0.06
     gusta
    -0.06
     Packs
    -0.06
     mill
    -0.06
     creations
    -0.06
    -CS
    -0.06
    кат
    -0.06
     assistants
    -0.06
     Preferences
    -0.06
    POSITIVE LOGITS
    663
    0.07
    止
    0.07
    __()↵↵
    0.07
    erne
    0.07
     �
    0.06
     своего
    0.06
    κολ
    0.06
     GM
    0.06
     справ
    0.06
    stderr
    0.06
    Act Density 0.001%

    No Known Activations