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

    Neuronpedia

    INDEX
    Explanations

    guess or accident

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    โร
    0.41
    瀟
    0.41
    轮
    0.39
    Connor
    0.38
     sic
    0.38
     flock
    0.38
    輪
    0.38
    Brown
    0.38
     nº
    0.38
     അര
    0.37
    POSITIVE LOGITS
    ANIUM
    0.41
     sooner
    0.40
     imagining
    0.39
    ᒡ
    0.39
    不起
    0.39
     менее
    0.38
     imagined
    0.37
     Gefahr
    0.36
    ovaž
    0.36
     enchanted
    0.36
    Act Density 0.000%

    No Known Activations