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

    Neuronpedia

    INDEX
    Explanations

    blockages and flooding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SCO
    -0.08
     IReadOnly
    -0.07
    _DRV
    -0.07
     XM
    -0.07
    .indent
    -0.06
    wealth
    -0.06
     elsewhere
    -0.06
    OND
    -0.06
     momentarily
    -0.06
    ᠴ
    -0.06
    POSITIVE LOGITS
    扩建
    0.08
    ialog
    0.07
    赞助
    0.07
    粑
    0.07
    必需
    0.07
    哈尔滨
    0.07
     besonders
    0.07
     wag
    0.07
    最早的
    0.07
     karma
    0.07
    Act Density 0.054%

    No Known Activations