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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onte
    -0.07
    Bước
    -0.06
     m
    -0.06
     کمک
    -0.06
    Regions
    -0.06
    	f
    -0.06
    モ
    -0.06
    つけ
    -0.06
    宜
    -0.06
     ב
    -0.06
    POSITIVE LOGITS
    that
    0.08
    äter
    0.07
     that
    0.07
     cria
    0.07
     INSTANCE
    0.07
    HAND
    0.07
    —that
    0.06
     Lowe
    0.06
     Sidney
    0.06
    ,Q
    0.06
    Act Density 0.022%

    No Known Activations