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

    Neuronpedia

    INDEX
    Explanations

    say math symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .clientX
    -0.06
    _teams
    -0.06
    _minutes
    -0.06
     взрос
    -0.06
     이런
    -0.06
    odo
    -0.06
     привы
    -0.06
    --↵
    -0.06
    EventType
    -0.06
     userList
    -0.06
    POSITIVE LOGITS
    ()",
    0.06
    ΟΥΣ
    0.06
     FI
    0.06
     Integr
    0.06
    邮箱
    0.06
     Accom
    0.06
    _cs
    0.06
     overarching
    0.06
     celebr
    0.06
     oppon
    0.06
    Act Density 0.029%

    No Known Activations