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

    Neuronpedia

    INDEX
    Explanations

    Firebase Messaging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OptionsMenu
    -0.07
    世上
    -0.07
     Bermuda
    -0.07
    쌓
    -0.07
    执
    -0.07
    荧
    -0.06
    脑
    -0.06
    并购
    -0.06
    드립니다
    -0.06
    驶
    -0.06
    POSITIVE LOGITS
    ocolate
    0.07
     Pix
    0.07
    (no
    0.07
     Sabha
    0.07
    ado
    0.07
    any
    0.06
     Coupon
    0.06
    	the
    0.06
    -ball
    0.06
    𝘰
    0.06
    Act Density 0.001%

    No Known Activations