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

    Neuronpedia

    INDEX
    Explanations

    flossing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ld
    0.66
     (
    0.65
    ;
    0.63
    ir
    0.57
    irl
    0.56
    !
    0.55
    ,
    0.55
    clk
    0.54
    :
    0.54
     circle
    0.53
    POSITIVE LOGITS
     mentors
    0.76
    osomes
    0.75
     floss
    0.75
    َی
    0.74
     Tige
    0.74
     Hase
    0.73
    apods
    0.73
     канторы
    0.72
     Okan
    0.72
    áte
    0.71
    Act Density 0.001%

    No Known Activations