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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     khỏi
    -0.06
    Minimal
    -0.06
     generic
    -0.06
     Laurent
    -0.06
    mitted
    -0.06
    duğu
    -0.06
     salary
    -0.06
    -positive
    -0.06
    Experience
    -0.06
     Held
    -0.06
    POSITIVE LOGITS
    0.07
     бл
    0.07
     NEG
    0.07
     XR
    0.06
     професси
    0.06
     필
    0.06
    DataTask
    0.06
     "));↵
    0.06
    _disk
    0.06
    _BOUND
    0.06
    Act Density 0.033%

    No Known Activations