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

    Neuronpedia

    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triệu
    -0.07
    Identification
    -0.07
    .isPlaying
    -0.06
    anyl
    -0.06
     化
    -0.06
    _step
    -0.06
     đỡ
    -0.06
    _axis
    -0.06
     Aside
    -0.06
     reco
    -0.06
    POSITIVE LOGITS
     ToolStrip
    0.07
     πραγμα
    0.06
    但是
    0.06
     подт
    0.06
    nel
    0.06
     Spokane
    0.06
    泛
    0.06
    kola
    0.06
    >.
    0.06
     Loft
    0.06
    Act Density 0.005%

    No Known Activations