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

    Neuronpedia

    INDEX
    Explanations

    concepts related to learning and memory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mín
    0.46
     agric
    0.45
     prêts
    0.45
     accrue
    0.44
     educate
    0.44
     prête
    0.43
     accumulate
    0.43
     спорта
    0.43
     entrer
    0.43
     résulte
    0.43
    POSITIVE LOGITS
    f
    0.49
    dark
    0.49
    shadow
    0.46
    ghost
    0.46
     প্রতিদ্বন্দ্ব
    0.46
     unveils
    0.46
     Nagata
    0.44
    ses
    0.44
    elligent
    0.44
    iy
    0.44
    Act Density 0.002%

    No Known Activations