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

    Neuronpedia

    INDEX
    Explanations

    Cookie policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thunder
    -0.06
    _complete
    -0.06
    imeters
    -0.06
    管理和
    -0.06
    -provider
    -0.06
    trys
    -0.06
    -breaking
    -0.06
    银川
    -0.06
    /th
    -0.06
     Bre
    -0.06
    POSITIVE LOGITS
     polarity
    0.07
    IP
    0.07
    作者
    0.07
     Pipeline
    0.07
    头顶
    0.07
    Desktop
    0.07
    حكيم
    0.07
    ᙳ
    0.07
     noises
    0.07
    (arr
    0.06
    Act Density 0.008%

    No Known Activations