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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тем
    -0.08
    äßig
    -0.07
    ani
    -0.07
     июля
    -0.07
    -Smith
    -0.07
     próximo
    -0.07
    .UserName
    -0.07
    <this
    -0.07
    estre
    -0.07
     אישית
    -0.07
    POSITIVE LOGITS
     Logical
    0.08
    Journal
    0.07
    #![
    0.07
     LC
    0.07
    预算
    0.07
     RMS
    0.07
    Sorted
    0.07
    抵押
    0.07
    .EVENT
    0.07
    一事
    0.07
    Act Density 0.296%

    No Known Activations