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

    Neuronpedia

    INDEX
    Explanations

    dirname

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "That
    -0.07
     Πρό
    -0.06
    "Well
    -0.06
     ze
    -0.06
     sushi
    -0.06
    Yet
    -0.06
     Reese
    -0.06
    .minecraft
    -0.06
     Clear
    -0.06
    -0.06
    POSITIVE LOGITS
    .dirname
    0.07
     Television
    0.07
    azon
    0.07
    Div
    0.07
    μαν
    0.07
     sperm
    0.07
    cluding
    0.07
     sürede
    0.06
     внутріш
    0.06
    jourd
    0.06
    Act Density 0.001%

    No Known Activations