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

    Neuronpedia

    INDEX
    Explanations

    various topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    达到
    -0.08
     manpower
    -0.07
    έντ
    -0.06
    �
    -0.06
    財
    -0.06
    황
    -0.06
     })),↵
    -0.06
     παι
    -0.06
     Mediterranean
    -0.06
    iete
    -0.06
    POSITIVE LOGITS
    abilir
    0.08
     Britann
    0.07
    шего
    0.06
     JUST
    0.06
    [^
    0.06
    	sc
    0.06
    掉
    0.06
    ...</
    0.06
    (args
    0.06
    (poly
    0.06
    Act Density 0.000%

    No Known Activations