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

    Neuronpedia

    INDEX
    Explanations

    plugin

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    覆
    0.57
     ły
    0.54
    ILERS
    0.54
    Wires
    0.52
    经理
    0.52
    serializers
    0.52
    collections
    0.51
    击
    0.51
    鞄
    0.51
    anny
    0.50
    POSITIVE LOGITS
     plugin
    0.83
    plugin
    0.80
     source
    0.79
     SOURCE
    0.73
     Plugin
    0.73
    remark
    0.69
     remark
    0.68
     Source
    0.68
    source
    0.66
    Source
    0.65
    Act Density 0.000%

    No Known Activations