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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ,retain
    -0.07
    Recipe
    -0.07
    獲
    -0.07
    уры
    -0.06
     esteemed
    -0.06
     lesions
    -0.06
    _SRV
    -0.06
     prostřed
    -0.06
    Compar
    -0.06
    POSITIVE LOGITS
    �
    0.06
     Pry
    0.06
     absolut
    0.06
    _inds
    0.06
    ?>↵↵
    0.06
     phận
    0.06
    _seconds
    0.06
    >()↵
    0.06
    řeb
    0.06
    ानक
    0.05
    Act Density 0.014%

    No Known Activations