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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     withdrew
    -0.07
     shirt
    -0.07
    ROW
    -0.07
    メリカ
    -0.06
    ecal
    -0.06
    (R
    -0.06
    КА
    -0.06
     ambiente
    -0.06
     Perspective
    -0.06
     tsp
    -0.06
    POSITIVE LOGITS
     accordion
    0.06
     ضد
    0.06
     sucess
    0.06
     动
    0.06
     분석
    0.06
    _CI
    0.06
    _DIRECTION
    0.06
     obrov
    0.06
    omin
    0.06
    操作
    0.06
    Act Density 0.000%

    No Known Activations