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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‌س
    -0.07
     myself
    -0.07
     Kia
    -0.07
    odd
    -0.06
     Barton
    -0.06
    emale
    -0.06
    YYY
    -0.06
    ovky
    -0.06
    unday
    -0.06
     історії
    -0.06
    POSITIVE LOGITS
    .isVisible
    0.07
     tt
    0.07
    ANGLES
    0.07
     inv
    0.07
     chví
    0.06
    ’e
    0.06
    .“↵↵
    0.06
     concess
    0.06
     tabel
    0.06
     surre
    0.06
    Act Density 0.155%

    No Known Activations