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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itemId
    -0.07
    _EOL
    -0.06
    ')]
    -0.06
     considerable
    -0.06
     epoll
    -0.06
     audience
    -0.06
    Battery
    -0.06
    ią
    -0.06
     entire
    -0.06
    LAY
    -0.06
    POSITIVE LOGITS
     scav
    0.06
    キング
    0.06
     whatever
    0.06
     assisted
    0.06
    แบบ
    0.06
     vibrant
    0.06
     clipped
    0.06
     statically
    0.05
     اجر
    0.05
     dejting
    0.05
    Act Density 0.052%

    No Known Activations