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

    Neuronpedia

    INDEX
    Explanations

    macOS interface elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waarde
    0.36
     lair
    0.35
    in
    0.34
     daarna
    0.34
     relatório
    0.34
    ,
    0.34
     सूर्य
    0.33
     odio
    0.33
    -
    0.33
     objectifs
    0.33
    POSITIVE LOGITS
    a
    0.50
    s
    0.49
    the
    0.43
    effects
    0.41
    ط
    0.41
    Stadium
    0.40
    tv
    0.40
    t
    0.40
    r
    0.39
    1
    0.39
    Act Density 0.000%

    No Known Activations