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

    Neuronpedia

    INDEX
    Explanations

    Recent news/current events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ió
    -0.07
    emporary
    -0.07
    いか
    -0.06
    _er
    -0.06
    .pt
    -0.06
    _io
    -0.06
    elho
    -0.06
    inness
    -0.06
     Weapon
    -0.06
    론
    -0.06
    POSITIVE LOGITS
    KindOfClass
    0.08
     náz
    0.07
    ?><
    0.07
    dataType
    0.06
     iceberg
    0.06
     Detroit
    0.06
    (tp
    0.06
    ?]
    0.06
    .sensor
    0.06
    东
    0.06
    Act Density 0.085%

    No Known Activations