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

    Neuronpedia

    INDEX
    Explanations

    looking away/down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    papers
    -0.07
     Liberia
    -0.06
    集
    -0.06
    -neutral
    -0.06
    ‐
    -0.06
    紧
    -0.06
    禮
    -0.06
    .partition
    -0.06
     cockpit
    -0.06
    COVER
    -0.06
    POSITIVE LOGITS
     Verm
    0.07
     خانم
    0.07
    Lazy
    0.07
    pellier
    0.07
     Герм
    0.06
    ーズ
    0.06
    authentication
    0.06
     singled
    0.06
     Gloss
    0.06
     öz
    0.06
    Act Density 0.082%

    No Known Activations