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

    Neuronpedia

    INDEX
    Explanations

    mg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    什么事情
    -0.08
     abc
    -0.08
    两级
    -0.08
    后面的
    -0.08
    ใด
    -0.07
     mildly
    -0.07
     suspicious
    -0.07
     outer
    -0.07
     invoking
    -0.07
     io
    -0.07
    POSITIVE LOGITS
    𝙟
    0.07
    .Invariant
    0.07
    _Out
    0.07
    幖
    0.07
     Contractors
    0.07
    _gateway
    0.06
     lived
    0.06
    zure
    0.06
     JV
    0.06
    Contract
    0.06
    Act Density 0.003%

    No Known Activations