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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Re
    -0.08
    (response
    -0.08
    aktu
    -0.07
     siblings
    -0.07
     Rel
    -0.06
    expand
    -0.06
     giao
    -0.06
    thumbnails
    -0.06
     marginBottom
    -0.06
    เคล
    -0.06
    POSITIVE LOGITS
    _por
    0.07
    각
    0.07
    套
    0.06
    限
    0.06
     conjug
    0.06
    )]);↵
    0.06
    uggest
    0.06
     proficiency
    0.06
     diets
    0.05
     là
    0.05
    Act Density 0.008%

    No Known Activations