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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	params
    -0.06
    	unsigned
    -0.06
     米
    -0.06
     commenc
    -0.06
    'na
    -0.06
    Ос
    -0.06
    差
    -0.06
     crest
    -0.06
    cdecl
    -0.06
    ’na
    -0.06
    POSITIVE LOGITS
     PACK
    0.07
    ]+$
    0.06
    insic
    0.06
     padding
    0.06
    UTURE
    0.06
     OT
    0.06
     gst
    0.06
    ICIENT
    0.06
    26
    0.06
    Ậ
    0.06
    Act Density 0.075%

    No Known Activations