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
    哥伦
    -0.08
     pthread
    -0.07
    nn
    -0.07
    𝐢
    -0.07
    fortunately
    -0.07
     projekt
    -0.07
     Probably
    -0.07
    elden
    -0.06
     Lookup
    -0.06
     ConfigureServices
    -0.06
    POSITIVE LOGITS
    _DOWN
    0.08
    _ADAPTER
    0.07
     DATE
    0.07
    保留
    0.07
     Shut
    0.07
     penalty
    0.07
    最关键
    0.07
     annihil
    0.07
    从业
    0.07
     Ax
    0.07
    Act Density 0.334%

    No Known Activations