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

    Neuronpedia

    INDEX
    Explanations

    COMMENT clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    deposit
    0.54
    voorbeeld
    0.47
     Север
    0.47
    political
    0.47
    法の
    0.47
    route
    0.46
    rystals
    0.46
    времен
    0.45
    semos
    0.45
    Northern
    0.44
    POSITIVE LOGITS
     Willy
    0.55
     Straw
    0.54
     ai
    0.54
     tr
    0.54
     ar
    0.53
     a
    0.51
     ghi
    0.51
     compass
    0.50
     Marietta
    0.50
     aria
    0.49
    Act Density 0.001%

    No Known Activations