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

    Neuronpedia

    INDEX
    Explanations

    represent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وإذا
    -0.07
     도
    -0.07
     deficiencies
    -0.07
     highways
    -0.07
    大致
    -0.07
    不由
    -0.06
    根基
    -0.06
     خاصة
    -0.06
     etwa
    -0.06
     Southeast
    -0.06
    POSITIVE LOGITS
     prm
    0.08
    命名
    0.07
    volent
    0.07
     presenter
    0.07
     mascara
    0.07
    SceneManager
    0.07
     belang
    0.07
    ying
    0.07
     ⓘ
    0.07
     Paging
    0.07
    Act Density 0.036%

    No Known Activations