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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Serv
    -0.08
    SetUp
    -0.07
    ованих
    -0.07
     NumberOf
    -0.07
    _attack
    -0.07
    _float
    -0.06
    เพ
    -0.06
     incent
    -0.06
     HeaderComponent
    -0.06
     pharmaceutical
    -0.06
    POSITIVE LOGITS
     ge
    0.07
    漫
    0.06
    abeth
    0.06
    .coin
    0.06
     giám
    0.05
    dad
    0.05
     InternalEnumerator
    0.05
    Leo
    0.05
    resco
    0.05
    รรม
    0.05
    Act Density 0.001%

    No Known Activations