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

    Neuronpedia

    INDEX
    Explanations

    JSON.stringify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    2.58
    dont
    2.16
    senha
    2.14
    দৈ
    2.13
     overshadowed
    2.12
     lobe
    2.06
    triggered
    2.04
    %>%
    2.03
    های
    2.01
    nof
    2.01
    POSITIVE LOGITS
    ać
    2.33
    eing
    2.28
    ein
    2.06
    ва
    2.02
    2.02
    \%).
    2.01
    ece
    1.92
    in
    1.92
    р
    1.92
    eol
    1.90
    Act Density 0.001%

    No Known Activations