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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �습니다
    -0.07
    _drop
    -0.07
     intrigued
    -0.06
    ApiClient
    -0.06
    .vocab
    -0.06
     яр
    -0.06
    -focused
    -0.06
     된다
    -0.06
     Img
    -0.06
    _dt
    -0.06
    POSITIVE LOGITS
    -input
    0.07
     ℝ
    0.07
     &:
    0.07
    LocalStorage
    0.06
    ğan
    0.06
    igrated
    0.06
     setLoading
    0.06
     campos
    0.06
    اح
    0.06
    (EXIT
    0.06
    Act Density 0.011%

    No Known Activations