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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evolving
    -0.07
    	h
    -0.07
    -ranked
    -0.06
     polic
    -0.06
    私の
    -0.06
    цион
    -0.06
     ріш
    -0.06
    รษ
    -0.06
     Кам
    -0.06
    cow
    -0.06
    POSITIVE LOGITS
     Sailor
    0.07
    用
    0.06
    451
    0.06
     imaginable
    0.06
    307
    0.06
     Ton
    0.06
     genius
    0.06
     مخروط
    0.06
    лага
    0.06
    ;.
    0.06
    Act Density 0.000%

    No Known Activations