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

    Neuronpedia

    INDEX
    Explanations

    visit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maintenant
    -0.08
     Meadows
    -0.07
     facilitating
    -0.07
    enty
    -0.07
     世
    -0.07
    ROUP
    -0.06
    _logical
    -0.06
    _reports
    -0.06
    来
    -0.06
    -rise
    -0.06
    POSITIVE LOGITS
    :red
    0.06
     обс
    0.06
     phon
    0.06
     zel
    0.06
    ._
    0.06
     italian
    0.06
     xOffset
    0.06
     trimmed
    0.06
     shrugged
    0.06
    ΑΡ
    0.06
    Act Density 0.028%

    No Known Activations