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

    Neuronpedia

    INDEX
    Explanations

    structured data descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hav
    -0.10
     conson
    -0.09
    \n
    -0.08
    ext
    -0.08
     hare
    -0.08
    \u
    -0.08
     Goodman
    -0.08
     Boom
    -0.08
    panion
    -0.07
    roman
    -0.07
    POSITIVE LOGITS
     |
    0.10
    égor
    0.09
    ¦æĥħ
    0.09
    ¶Į
    0.09
    ENTE
    0.09
    ><![
    0.09
    ¥¤
    0.09
    reib
    0.08
    AdapterManager
    0.08
    =array
    0.08
    Act Density 0.017%

    No Known Activations