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

    Neuronpedia

    INDEX
    Explanations

    swimwear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hatır
    -0.08
     incentives
    -0.07
    LED
    -0.07
    ricks
    -0.07
     explosions
    -0.07
    인트
    -0.07
    leet
    -0.07
     mắt
    -0.07
     reserve
    -0.07
     pazar
    -0.07
    POSITIVE LOGITS
     bikini
    0.10
     Bik
    0.07
    เภ
    0.07
    ipheral
    0.06
    Peripheral
    0.06
     Keto
    0.06
    .By
    0.06
     Shah
    0.06
     discriminate
    0.06
    ﾆ
    0.06
    Act Density 0.005%

    No Known Activations