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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -print
    -0.07
     seller
    -0.07
    obox
    -0.07
    iders
    -0.07
     status
    -0.06
     Child
    -0.06
    childs
    -0.06
     arrayList
    -0.06
    early
    -0.06
     seus
    -0.06
    POSITIVE LOGITS
     dư
    0.07
    �
    0.06
    演
    0.06
    „ظ
    0.06
     BufferedImage
    0.06
    _intent
    0.06
    ’on
    0.05
     Tor
    0.05
    雷
    0.05
    .wav
    0.05
    Act Density 0.019%

    No Known Activations