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

    Neuronpedia

    INDEX
    Explanations

    sum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yanlı
    -0.08
    _pen
    -0.08
     вам
    -0.07
    伶
    -0.07
     ];
    -0.07
    匮乏
    -0.07
     miser
    -0.07
    /icon
    -0.07
    配音
    -0.07
    经济学家
    -0.07
    POSITIVE LOGITS
    akra
    0.07
    	sub
    0.07
    /db
    0.07
    .static
    0.06
     debut
    0.06
    Age
    0.06
    UCCESS
    0.06
    quet
    0.06
     alte
    0.06
    those
    0.06
    Act Density 0.017%

    No Known Activations