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

    Neuronpedia

    INDEX
    Explanations

    navigation containers and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nav
    0.44
     Navarra
    0.39
     svij
    0.38
    Ｉ
    0.38
     Nav
    0.37
    naval
    0.37
    acart
    0.37
    erman
    0.37
     nav
    0.36
    ناو
    0.36
    POSITIVE LOGITS
    BAR
    0.44
     کنکریاں
    0.41
     DO
    0.40
    鉄道
    0.40
     railing
    0.39
     പഴ
    0.39
     தட
    0.39
    dot
    0.38
     EXISTS
    0.38
    Dots
    0.38
    Act Density 0.001%

    No Known Activations