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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ду
    -0.07
    ありがとうござ
    -0.07
    �
    -0.07
    anim
    -0.07
    _TRANSACTION
    -0.06
     Anthem
    -0.06
     uč
    -0.06
    INGLE
    -0.06
     Unified
    -0.06
     grieving
    -0.06
    POSITIVE LOGITS
    )))↵↵↵
    0.07
    孩子
    0.06
    ))))↵↵
    0.06
     région
    0.06
    *******
↵
    0.06
    _ALLOWED
    0.06
     gorge
    0.06
    (env
    0.06
    TableView
    0.06
     possessed
    0.06
    Act Density 0.305%

    No Known Activations