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

    Neuronpedia

    INDEX
    Explanations

    Code and text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sailors
    -0.07
     FALL
    -0.07
     spend
    -0.07
     μέρος
    -0.06
     Shooting
    -0.06
    行政
    -0.06
    most
    -0.06
     heaps
    -0.06
    cest
    -0.06
    strained
    -0.06
    POSITIVE LOGITS
    isque
    0.07
    意
    0.07
    DATA
    0.06
     출연
    0.06
     totalement
    0.06
     Çev
    0.06
    capability
    0.06
     NoSuchElementException
    0.06
    ensi
    0.06
    РСР
    0.06
    Act Density 0.000%

    No Known Activations