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

    Neuronpedia

    INDEX
    Explanations

    lumin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olid
    -0.07
    void
    -0.07
    공
    -0.07
     purity
    -0.07
    ISTER
    -0.06
     notes
    -0.06
     Leap
    -0.06
     nv
    -0.06
    톡
    -0.06
     원
    -0.06
    POSITIVE LOGITS
    .mi
    0.06
     angled
    0.06
     slippery
    0.06
     premature
    0.06
     abi
    0.06
     Lamar
    0.06
    лся
    0.06
    Acknowled
    0.06
    .additional
    0.06
    岁
    0.06
    Act Density 0.002%

    No Known Activations