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

    Neuronpedia

    INDEX
    Explanations

    migrate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    依據
    -0.07
     eq
    -0.07
    oke
    -0.07
    번째
    -0.07
     Cory
    -0.07
    (username
    -0.07
     uy
    -0.07
    CNN
    -0.07
    	UINT
    -0.07
     ú
    -0.07
    POSITIVE LOGITS
    校友
    0.07
    闭环
    0.07
    useRalative
    0.07
    )||
    0.07
    🈲
    0.07
     IMPORT
    0.07
     스스
    0.06
     terrestrial
    0.06
     autor
    0.06
     Mayer
    0.06
    Act Density 0.004%

    No Known Activations