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

    Neuronpedia

    INDEX
    Explanations

    past events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    排序
    -0.07
    几乎
    -0.07
    chu
    -0.07
    382
    -0.06
     all
    -0.06
    _prot
    -0.06
    409
    -0.06
    -(
    -0.06
     Най
    -0.06
     찬
    -0.06
    POSITIVE LOGITS
    JM
    0.07
    _index
    0.07
     waivers
    0.07
    darwin
    0.07
    ,GL
    0.06
     dataArray
    0.06
     readme
    0.06
     knows
    0.06
     dosage
    0.06
    .Index
    0.06
    Act Density 0.101%

    No Known Activations