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

    Neuronpedia

    INDEX
    Explanations

    scientific publication references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exp
    -0.07
    -high
    -0.07
    IPS
    -0.07
     revise
    -0.06
     Libertarian
    -0.06
     Tips
    -0.06
    tp
    -0.06
     indexing
    -0.06
    Info
    -0.06
    thumbnail
    -0.06
    POSITIVE LOGITS
    .djang
    0.07
    .currentTimeMillis
    0.06
    スティ
    0.06
     WideString
    0.06
    Invoker
    0.06
    _bg
    0.06
    vic
    0.06
    CallableWrapper
    0.06
    わたし
    0.06
    ecessary
    0.06
    Act Density 0.002%

    No Known Activations