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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brave
    -0.07
    insk
    -0.07
    QUEST
    -0.07
    DataSet
    -0.07
    papers
    -0.07
    🗺
    -0.06
    _PROVID
    -0.06
    磋
    -0.06
    KeySpec
    -0.06
     Executor
    -0.06
    POSITIVE LOGITS
    皱纹
    0.08
    .cg
    0.07
     coating
    0.07
     lớp
    0.07
     đạo
    0.07
    .dex
    0.06
    ujet
    0.06
     QLabel
    0.06
     equally
    0.06
    紧迫
    0.06
    Act Density 0.004%

    No Known Activations