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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    senal
    -0.06
    ookies
    -0.06
     doorway
    -0.06
    670
    -0.06
    utr
    -0.06
    StringEncoding
    -0.06
    agged
    -0.06
    ORIZ
    -0.05
    ceptive
    -0.05
    221
    -0.05
    POSITIVE LOGITS
     Investigations
    0.07
     Pee
    0.07
    undreds
    0.07
     head
    0.07
    =name
    0.07
     crest
    0.07
     overdose
    0.07
    	Created
    0.06
    Tên
    0.06
     hacks
    0.06
    Act Density 0.004%

    No Known Activations