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

    Neuronpedia

    INDEX
    Explanations

    language and dialects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xes
    -0.07
    Build
    -0.07
    结构
    -0.06
     иногда
    -0.06
    Excellent
    -0.06
    VISION
    -0.06
    Tower
    -0.06
     hoje
    -0.06
    �
    -0.06
     dishonest
    -0.06
    POSITIVE LOGITS
     Fame
    0.06
    osh
    0.06
    (Account
    0.06
    nev
    0.06
     EOF
    0.06
     getPlayer
    0.06
     تکن
    0.06
    ій
    0.06
    iatric
    0.05
    ropping
    0.05
    Act Density 0.029%

    No Known Activations