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

    Neuronpedia

    INDEX
    Explanations

    in/of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recognized
    -0.07
     civil
    -0.06
    	k
    -0.06
     Handler
    -0.06
     Investigation
    -0.06
    -vertical
    -0.06
     suggests
    -0.06
     hands
    -0.06
    ”，
    -0.06
    mî
    -0.06
    POSITIVE LOGITS
    .Blocks
    0.08
    quota
    0.08
    ože
    0.07
    öy
    0.07
    stalk
    0.07
     FStar
    0.07
     Tỉnh
    0.07
    اوه
    0.06
    imd
    0.06
     Bahamas
    0.06
    Act Density 0.011%

    No Known Activations