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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ups
    -0.06
    [A
    -0.06
    .until
    -0.06
     soruml
    -0.06
    ся
    -0.06
    _possible
    -0.06
    .access
    -0.06
     candles
    -0.06
    /umd
    -0.06
     DataGridView
    -0.06
    POSITIVE LOGITS
    alcon
    0.06
    十五
    0.06
     coherence
    0.06
    角
    0.06
    ENCE
    0.06
    ฒ
    0.06
     recruiters
    0.06
     etwa
    0.06
    服
    0.06
     στον
    0.06
    Act Density 0.084%

    No Known Activations