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

    Neuronpedia

    INDEX
    Explanations

    Capital letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ش
    -0.07
     Farms
    -0.07
     Roller
    -0.06
     reports
    -0.06
     recommendation
    -0.06
    Story
    -0.06
     TEXT
    -0.06
     approximation
    -0.06
     peaks
    -0.06
     fly
    -0.06
    POSITIVE LOGITS
    BTTag
    0.07
     یعنی
    0.06
    nten
    0.06
     naï
    0.06
    "});↵
    0.06
    یدن
    0.06
    .UserId
    0.06
     Wolfgang
    0.06
      
↵
↵
    0.06
    .Sockets
    0.06
    Act Density 0.012%

    No Known Activations