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

    Neuronpedia

    INDEX
    Explanations

    states, outcomes, or conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    錤
    0.44
    眝
    0.44
     специфи
    0.43
     bolstering
    0.43
    珢
    0.42
    挀
    0.42
    俦
    0.42
    ปลี่ยน
    0.42
     minimale
    0.42
     overarching
    0.41
    POSITIVE LOGITS
    ，
    0.59
    ！
    0.59
     according
    0.58
     anyway
    0.57
     ，
    0.56
    ；
    0.55
     before
    0.54
    !
    0.54
    .
    0.54
    。
    0.54
    Act Density 0.011%

    No Known Activations