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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slogan
    -0.07
     restau
    -0.07
     Dawson
    -0.06
    ulen
    -0.06
    /ad
    -0.06
     devam
    -0.06
     kicker
    -0.06
    III
    -0.06
    -ROM
    -0.06
     ud
    -0.06
    POSITIVE LOGITS
     karakter
    0.06
    ливості
    0.06
     cenu
    0.06
    (ERROR
    0.06
    ние
    0.06
    Candidate
    0.06
       ↵    ↵
    0.06
    xC
    0.06
    .toHexString
    0.06
     [&
    0.06
    Act Density 0.002%

    No Known Activations