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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ett
    -0.07
    ši
    -0.07
    olf
    -0.06
     Bard
    -0.06
     répond
    -0.06
     intervention
    -0.06
    allon
    -0.06
    Helmet
    -0.06
     Truck
    -0.06
     hitters
    -0.06
    POSITIVE LOGITS
    __
↵
    0.07
    pb
    0.07
    .keywords
    0.07
    |()↵
    0.07
    DAL
    0.06
    uably
    0.06
    588
    0.06
     DWORD
    0.06
    fds
    0.06
     pł
    0.06
    Act Density 0.002%

    No Known Activations