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

    Neuronpedia

    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cé
    -0.08
    emplace
    -0.07
     And
    -0.07
     και
    -0.07
    意思
    -0.07
     Анд
    -0.07
     piracy
    -0.06
    gn
    -0.06
     Lori
    -0.06
    gıç
    -0.06
    POSITIVE LOGITS
     mostly
    0.06
     thrilling
    0.06
     Ware
    0.06
    _method
    0.06
     cams
    0.06
     regression
    0.06
    _UNIFORM
    0.06
     Monkey
    0.06
     []↵
    0.06
     medical
    0.06
    Act Density 0.266%

    No Known Activations