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

    Neuronpedia

    INDEX
    Explanations

    user-provided premises or scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (:
    0.53
     &:
    0.50
    कोष्ठ
    0.50
     데이터
    0.49
     момент
    0.48
     momen
    0.48
     NPTypeCode
    0.48
     플레이
    0.48
    पीरिय
    0.48
     TouchUtils
    0.48
    POSITIVE LOGITS
    。
    0.54
    ya
    0.49
    ma
    0.46
    al
    0.45
    nature
    0.43
    cob
    0.43
    Cob
    0.43
    ent
    0.42
    नुसार
    0.42
    et
    0.42
    Act Density 0.008%

    No Known Activations