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

    Neuronpedia

    INDEX
    Explanations

    multiple nodes and servers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ỡng
    0.43
     reconfiguration
    0.43
    Mig
    0.42
     Periodic
    0.41
    Parallel
    0.40
    Camb
    0.38
    Harm
    0.38
    災害
    0.38
    パリ
    0.38
    Periodic
    0.38
    POSITIVE LOGITS
     node
    0.83
     Nodes
    0.78
     nodes
    0.77
    node
    0.73
     Node
    0.68
    Nodes
    0.64
    Node
    0.62
    nodes
    0.61
    节点
    0.59
    NODE
    0.59
    Act Density 0.030%

    No Known Activations