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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vention
    -0.07
     Мин
    -0.07
     Navigation
    -0.07
     interdisciplinary
    -0.06
     interception
    -0.06
     exploring
    -0.06
    .getVersion
    -0.06
    苏宁
    -0.06
     landing
    -0.06
     Landing
    -0.06
    POSITIVE LOGITS
    𝘿
    0.07
    retched
    0.07
     produits
    0.07
    +d
    0.07
    hea
    0.07
    trys
    0.07
    trägt
    0.07
     kos
    0.07
    YEAR
    0.07
    resa
    0.07
    Act Density 0.056%

    No Known Activations