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

    Neuronpedia

    INDEX
    Explanations

    Mentions specific nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ‘‘
    -0.08
     akibat
    -0.08
     raging
    -0.08
     bunun
    -0.08
     chased
    -0.07
     jika
    -0.07
     “
    -0.07
    -0.07
     Jika
    -0.07
    ZS
    -0.07
    POSITIVE LOGITS
     research
    0.08
     rental
    0.08
    nen
    0.07
    ורות
    0.07
    ನ್ನು
    0.07
    וא
    0.07
    0.07
    ราย
    0.07
    192
    0.07
     által
    0.07
    Act Density 0.120%
    No Known Activations