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

    Neuronpedia

    INDEX
    Explanations

    Dart code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     אוהבת
    -0.07
    ซอ
    -0.07
    있
    -0.07
    _FULLSCREEN
    -0.07
    耕地
    -0.07
     Filipino
    -0.07
    _-_
    -0.07
     Venezuel
    -0.07
     הולד
    -0.07
    ssue
    -0.07
    POSITIVE LOGITS
    عي
    0.07
    ani
    0.07
    cairo
    0.07
    聂
    0.07
     parti
    0.07
    الي
    0.07
    здрав
    0.07
    .Concat
    0.07
    يات
    0.06
    半
    0.06
    Act Density 0.016%

    No Known Activations