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

    Neuronpedia

    INDEX
    Explanations

    actions and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahanga
    0.46
     കാരണ
    0.45
    nucleon
    0.45
    Browsable
    0.43
    itories
    0.42
     重要
    0.42
    ліся
    0.42
     nucleons
    0.42
     나오는
    0.41
    ajou
    0.41
    POSITIVE LOGITS
     وتح
    0.49
     Indic
    0.48
     water
    0.44
     placer
    0.44
     Stopwatch
    0.44
     venit
    0.43
     volgens
    0.43
     Bl
    0.43
    च
    0.43
     con
    0.43
    Act Density 0.000%

    No Known Activations