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

    Neuronpedia

    INDEX
    Explanations

    University of, boonie hats, 박사가 사랑한

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    --“
    0.40
    ரிடம்
    0.38
    inité
    0.37
    ין
    0.37
     :"
    0.36
    ப்பட்டது
    0.36
    ੋ
    0.36
     newMovie
    0.36
    ondi
    0.35
    :")
    0.35
    POSITIVE LOGITS
    چ
    0.38
     Editors
    0.36
     ICP
    0.36
    se
    0.34
     Writers
    0.34
     esa
    0.34
     Outback
    0.33
     Essays
    0.33
    uterine
    0.33
     Ridd
    0.33
    Act Density 0.000%

    No Known Activations