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

    Neuronpedia

    INDEX
    Explanations

    if else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nếu
    0.46
    0.43
    iramente
    0.41
     کاسینو
    0.40
    䒑
    0.40
    बिलिटी
    0.39
    SIBILITIES
    0.39
     اگر
    0.38
     kalau
    0.38
    わりに
    0.37
    POSITIVE LOGITS
    ølge
    0.60
    rames
    0.58
    bbene
    0.48
     isn
    0.48
     exists
    0.48
     quiera
    0.47
     anyone
    0.47
     youre
    0.46
     ever
    0.46
    ecycle
    0.46
    Act Density 0.012%

    No Known Activations