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

    Neuronpedia

    INDEX
    Explanations

    defined or imagine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кров
    0.44
    Somos
    0.42
    Usually
    0.42
    害怕
    0.41
     সাধারণত
    0.40
    αρ
    0.39
    Prot
    0.39
    Epid
    0.39
    WhatsApp
    0.39
    There
    0.38
    POSITIVE LOGITS
     on
    0.58
     taped
    0.46
     East
    0.45
    richten
    0.44
     الشمس
    0.44
     Fulbright
    0.44
     el
    0.42
     Research
    0.42
    畐
    0.42
     Travels
    0.42
    Act Density 0.011%

    No Known Activations