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

    Neuronpedia

    INDEX
    Explanations

    street and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Que
    0.47
    NoStop
    0.45
    Healthy
    0.44
     Quebec
    0.44
    Straw
    0.44
    🛶
    0.42
     QUE
    0.40
    Act
    0.39
    Ket
    0.39
    ⛴
    0.38
    POSITIVE LOGITS
     ND
    0.55
     Snowdon
    0.54
     Mile
    0.54
     Milton
    0.49
     Dante
    0.47
     Mais
    0.47
     Plateau
    0.47
    Mile
    0.47
     nd
    0.46
     Out
    0.46
    Act Density 0.003%

    No Known Activations