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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    資
    -0.07
    ィ
    -0.06
    _idx
    -0.06
    얼
    -0.06
     Aside
    -0.06
     ApiResponse
    -0.06
    _major
    -0.06
     مسجد
    -0.06
    積
    -0.06
    aln
    -0.06
    POSITIVE LOGITS
     παρ
    0.06
     Enables
    0.06
    locking
    0.06
     Anast
    0.06
    Rew
    0.06
     ENG
    0.05
     hypers
    0.05
     Gameplay
    0.05
    .release
    0.05
     Packing
    0.05
    Act Density 0.155%

    No Known Activations