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

    Neuronpedia

    INDEX
    Explanations

    humor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     humane
    -0.07
    �
    -0.06
    )item
    -0.06
    ét
    -0.06
    .arch
    -0.06
     Monad
    -0.05
    zim
    -0.05
     omn
    -0.05
     crunchy
    -0.05
    =in
    -0.05
    POSITIVE LOGITS
     Worse
    0.07
     conoc
    0.07
    <(),
    0.07
     suppressing
    0.07
     Крас
    0.07
    geometry
    0.06
    .JpaRepository
    0.06
    лен
    0.06
     cousins
    0.06
     Teh
    0.06
    Act Density 0.056%

    No Known Activations