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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Me
    -0.08
     لأ
    -0.07
    _SEPARATOR
    -0.07
     RC
    -0.07
    技术支持
    -0.07
     actual
    -0.06
    axon
    -0.06
     encour
    -0.06
    .builders
    -0.06
     Cộng
    -0.06
    POSITIVE LOGITS
     //!
    0.07
    физ
    0.07
     GUILayout
    0.07
     Gates
    0.06
    蝉
    0.06
    相
    0.06
    实验
    0.06
     Fant
    0.06
    Detailed
    0.06
    .mem
    0.06
    Act Density 0.024%

    No Known Activations