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
    (dom
    -0.06
     Selbst
    -0.06
     Bec
    -0.06
    liche
    -0.06
    /free
    -0.06
    。この
    -0.06
    .Par
    -0.06
     cazzo
    -0.06
    ーデ
    -0.06
    antic
    -0.06
    POSITIVE LOGITS
     Graham
    0.07
     saint
    0.06
    	document
    0.06
     arg
    0.06
    ;",
    0.06
    lecture
    0.06
     shaking
    0.06
    >');
↵
    0.06
    "});↵
    0.06
     fopen
    0.06
    Act Density 0.005%

    No Known Activations