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

    Neuronpedia

    INDEX
    Explanations

    events and outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مح
    -0.07
    .bb
    -0.07
    _vals
    -0.07
     �
    -0.07
     RF
    -0.07
     lut
    -0.07
    互
    -0.06
    ोध
    -0.06
     Hod
    -0.06
    390
    -0.06
    POSITIVE LOGITS
    >↵↵↵
    0.07
     学
    0.07
    。↵↵↵↵↵↵
    0.07
     Position
    0.07
    Later
    0.06
     همکاری
    0.06
     لكل
    0.06
    kanı
    0.06
    ">${
    0.06
    ";↵↵↵
    0.06
    Act Density 0.191%

    No Known Activations