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

    Neuronpedia

    INDEX
    Explanations

    pointing spike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enem
    0.52
    atan
    0.49
    '
    0.49
    ،
    0.49
    اين
    0.47
    ichten
    0.47
    ıştır
    0.47
    </b>
    0.46
    |\
    0.46
    ultur
    0.46
    POSITIVE LOGITS
     Appalach
    0.45
     apprenticeship
    0.44
     Fusion
    0.43
     infringing
    0.42
     Thessalon
    0.41
     jaws
    0.41
     Sinclair
    0.41
     outrage
    0.41
    showinfo
    0.41
     ஒப்பு
    0.40
    Act Density 0.000%

    No Known Activations