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

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UpDown
    -0.07
    ingredients
    -0.06
     abyss
    -0.06
     lineno
    -0.06
    .DIS
    -0.06
    getDate
    -0.06
     Cummings
    -0.06
     funkc
    -0.06
    �
    -0.06
    ])/
    -0.06
    POSITIVE LOGITS
    жив
    0.08
    些
    0.07
     nests
    0.07
    modern
    0.07
    έα
    0.07
     той
    0.07
    羊
    0.07
    .events
    0.07
     fodder
    0.06
    iyor
    0.06
    Act Density 0.013%

    No Known Activations