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

    Neuronpedia

    INDEX
    Explanations

    incestuous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     школе
    0.51
     atendimento
    0.50
     男の子
    0.47
    ೮
    0.47
     जायेंगे
    0.44
     ogrom
    0.44
     inteiro
    0.43
     ремон
    0.43
     spineItem
    0.43
     ellipse
    0.42
    POSITIVE LOGITS
     modalités
    0.50
    Locks
    0.42
    vors
    0.41
    InBuffer
    0.40
    Power
    0.39
    طل
    0.38
     Lowe
    0.38
     Expressions
    0.38
     Insider
    0.38
     حاصل
    0.38
    Act Density 0.005%

    No Known Activations