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

    Neuronpedia

    INDEX
    Explanations

    URLs and domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     www
    0.42
    alogical
    0.38
    代目
    0.36
    imeo
    0.36
    .(*
    0.36
    ايبي
    0.35
    ysets
    0.35
    geoip
    0.35
    ᚐ
    0.35
    squareup
    0.34
    POSITIVE LOGITS
     {})
    0.36
     prioritise
    0.33
     hindi
    0.32
    滈
    0.31
     maine
    0.30
     {});
    0.30
     Hindi
    0.30
     weiterhin
    0.29
     مشتمل
    0.29
    窮
    0.29
    Act Density 0.017%

    No Known Activations