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

    Neuronpedia

    INDEX
    Explanations

    allows for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     টেলিভিশন
    0.52
    ঢাকা
    0.51
     苏
    0.51
     设备
    0.51
     janë
    0.50
     રીતે
    0.50
    gheatmap
    0.49
     सीखना
    0.49
     jsou
    0.48
    LetterLocation
    0.48
    POSITIVE LOGITS
    foot
    0.46
    <0xE3>
    0.45
    card
    0.44
    f
    0.43
    batt
    0.41
    ↵
    0.39
     '
    0.39
    5
    0.39
    fare
    0.39
    b
    0.39
    Act Density 0.001%

    No Known Activations