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
    )");
↵
    -0.07
     Week
    -0.06
    �始
    -0.06
     باشید
    -0.06
    ما
    -0.06
     sid
    -0.06
     humid
    -0.06
    ">-->↵
    -0.06
     ≥
    -0.06
    ARING
    -0.06
    POSITIVE LOGITS
     of
    0.08
     Vim
    0.07
    есп
    0.06
     Bbw
    0.06
    .makedirs
    0.06
    inoa
    0.06
    of
    0.06
     Corps
    0.06
     그리고
    0.06
    mekte
    0.06
    Act Density 0.080%

    No Known Activations