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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .controllers
    -0.06
     Mik
    -0.06
     Battle
    -0.06
     Sky
    -0.06
     roli
    -0.06
    (Random
    -0.06
    Mode
    -0.06
    Mont
    -0.06
     Jaw
    -0.06
    린
    -0.06
    POSITIVE LOGITS
    !).
    0.07
     moder
    0.07
     flavours
    0.06
    .
    0.06
    quota
    0.06
    osals
    0.06
     законодав
    0.06
    алог
    0.06
    Ă
    0.06
    .Predicate
    0.06
    Act Density 0.015%

    No Known Activations