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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icter
    -0.07
    윤
    -0.07
    aire
    -0.06
    �
    -0.06
     mon
    -0.06
    -google
    -0.06
    ペ
    -0.06
    ES
    -0.06
     disturbing
    -0.06
    TION
    -0.06
    POSITIVE LOGITS
    "C
    0.06
    "".
    0.06
     valve
    0.06
     "'.
    0.06
    {}↵
    0.06
    让
    0.06
     }()↵
    0.06
    	ctx
    0.06
    ,lat
    0.06
    kân
    0.06
    Act Density 0.011%

    No Known Activations