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

    Neuronpedia

    INDEX
    Explanations

    company products/services

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    あり
    -0.07
    になり
    -0.07
    elay
    -0.07
     Shopping
    -0.07
    utra
    -0.06
     đích
    -0.06
     Zum
    -0.06
     Teens
    -0.06
     irres
    -0.06
     textbook
    -0.06
    POSITIVE LOGITS
    withstanding
    0.07
    SED
    0.06
    _tem
    0.06
    rowned
    0.06
    spell
    0.06
    yses
    0.06
    ]";↵
    0.06
    _KeyPress
    0.06
     Ling
    0.06
    .scenes
    0.06
    Act Density 0.068%

    No Known Activations