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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bull
    -0.07
    	buff
    -0.07
     Crawford
    -0.07
     crew
    -0.06
    88
    -0.06
    tt
    -0.06
    bw
    -0.06
    ันทร
    -0.06
    ytt
    -0.06
    ott
    -0.06
    POSITIVE LOGITS
     index
    0.15
    Index
    0.13
     Index
    0.13
    index
    0.12
    	idx
    0.11
    .index
    0.11
    _index
    0.11
     idx
    0.11
    	index
    0.11
     INDEX
    0.10
    Act Density 0.031%

    No Known Activations