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

    Neuronpedia

    INDEX
    Explanations

    US legal appeals cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HOT
    -0.06
     faithful
    -0.06
    Logger
    -0.06
     cognition
    -0.06
     Authenticate
    -0.06
    _sum
    -0.06
     predictable
    -0.06
     pha
    -0.06
     summar
    -0.06
     Salon
    -0.06
    POSITIVE LOGITS
     nickel
    0.07
    此
    0.06
    ῦ
    0.06
    orang
    0.06
    xp
    0.06
    ляет
    0.06
     independently
    0.06
    _templates
    0.06
    _seat
    0.06
    /application
    0.06
    Act Density 0.006%

    No Known Activations