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

    Neuronpedia

    INDEX
    Explanations

    Advancements and increasing trends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     girlfriend
    -0.07
    =set
    -0.06
    Ｖ
    -0.06
    唐
    -0.06
    _logical
    -0.06
    trash
    -0.06
    CEO
    -0.06
    UGIN
    -0.06
     partic
    -0.06
    Cold
    -0.06
    POSITIVE LOGITS
     Jays
    0.07
    Functions
    0.07
     subjected
    0.07
    yards
    0.07
    ReuseIdentifier
    0.06
    阪
    0.06
     calves
    0.06
     Greeks
    0.06
     assembler
    0.06
    **
↵
    0.06
    Act Density 0.099%

    No Known Activations