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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Slide
    -0.07
    Gap
    -0.06
    .th
    -0.06
     repeal
    -0.06
    lí
    -0.06
     marketers
    -0.06
    _letter
    -0.06
    _balance
    -0.06
    бира
    -0.06
    ：<
    -0.06
    POSITIVE LOGITS
     yağ
    0.06
    .fire
    0.06
    št
    0.06
    ovy
    0.06
     batter
    0.06
    AGENT
    0.06
    nych
    0.06
    modx
    0.06
     FULL
    0.06
    Legendary
    0.06
    Act Density 0.001%

    No Known Activations