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

    Neuronpedia

    INDEX
    Explanations

    network

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Assistant
    -0.08
    빈
    -0.07
    題
    -0.07
    ㅡ
    -0.07
     Feast
    -0.07
    表现为
    -0.07
    を超
    -0.07
    �
    -0.07
    .provider
    -0.07
    -tab
    -0.07
    POSITIVE LOGITS
     network
    0.08
    롑
    0.07
     networks
    0.07
    0.07
    _named
    0.07
    搞得
    0.07
     najwięks
    0.07
     nit
    0.07
    몸
    0.07
     khám
    0.07
    Act Density 0.031%

    No Known Activations