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

    Neuronpedia

    INDEX
    Explanations

    Tea, especially oolong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    хов
    -0.07
    _STAGE
    -0.07
     hal
    -0.07
     caric
    -0.06
    official
    -0.06
    694
    -0.06
     TR
    -0.06
    .reserve
    -0.06
    .Team
    -0.06
    市
    -0.06
    POSITIVE LOGITS
     msm
    0.07
    ิท
    0.06
    ǐ
    0.06
    і
    0.06
    _logger
    0.06
     ILogger
    0.06
    enden
    0.06
     ارزی
    0.06
     inicio
    0.06
    нить
    0.06
    Act Density 0.010%

    No Known Activations