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

    Neuronpedia

    INDEX
    Explanations

    valid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ebony
    -0.07
     petroleum
    -0.07
    conference
    -0.07
    ardware
    -0.07
     eternity
    -0.07
    这款车
    -0.07
    Crear
    -0.07
    债权
    -0.06
    ;c
    -0.06
    "With
    -0.06
    POSITIVE LOGITS
     valid
    0.09
    (sv
    0.08
    ๋
    0.07
     Translator
    0.07
    发作
    0.07
    	mp
    0.07
    入围
    0.07
    脉
    0.06
    성
    0.06
    غال
    0.06
    Act Density 0.015%

    No Known Activations