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

    Neuronpedia

    INDEX
    Explanations

    by exposure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ({{
    0.66
    ouncing
    0.66
     cuadr
    0.66
    វិធី
    0.65
    cmml
    0.65
     ün
    0.65
    ຕົວ
    0.65
    न्स
    0.65
     उचल
    0.65
    ovní
    0.65
    POSITIVE LOGITS
    ез
    0.71
    炜
    0.69
    द्
    0.68
     подозре
    0.68
     छापा
    0.67
     Lazarus
    0.67
    Pid
    0.66
     trabalh
    0.66
    езд
    0.64
     рід
    0.64
    Act Density 0.001%

    No Known Activations