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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Through
    -0.07
     Rhe
    -0.07
    嗯
    -0.07
    	inline
    -0.07
     ARP
    -0.06
     �
    -0.06
    ?id
    -0.06
    ('~
    -0.06
     opioid
    -0.06
     Through
    -0.06
    POSITIVE LOGITS
    ันวาคม
    0.07
    мон
    0.06
    ]}
    0.06
    clidean
    0.06
     Shade
    0.06
     лік
    0.06
    ----↵
    0.06
    決
    0.06
    ]}"
    0.06
    ̂
    0.06
    Act Density 0.262%

    No Known Activations