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

    Neuronpedia

    INDEX
    Explanations

    numbered lists and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     femen
    0.39
     erweitert
    0.37
     cartera
    0.36
     adequate
    0.36
    𝒂
    0.36
     Rhiz
    0.35
     responden
    0.35
     Tore
    0.35
    勮
    0.34
     berd
    0.34
    POSITIVE LOGITS
    as
    0.51
    an
    0.46
    is
    0.45
    ர்
    0.45
    ص
    0.43
    ीकृत
    0.43
    ся
    0.42
    i
    0.40
    ре
    0.40
    elden
    0.40
    Act Density 0.370%

    No Known Activations