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

    Neuronpedia

    INDEX
    Explanations

    token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bender
    -0.08
    ieran
    -0.07
    (ti
    -0.07
     Fi
    -0.07
    腹
    -0.07
     Fade
    -0.07
    oward
    -0.07
    	sd
    -0.07
    лом
    -0.06
    world
    -0.06
    POSITIVE LOGITS
     setups
    0.08
     authenticated
    0.07
    	un
    0.07
    >';
↵
    0.07
    称号
    0.06
     Orb
    0.06
     analysts
    0.06
     acts
    0.06
     />;↵
    0.06
     ...↵↵
    0.06
    Act Density 0.002%

    No Known Activations