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

    Neuronpedia

    INDEX
    Explanations

    Organizations, places, titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _config
    -0.07
    selected
    -0.06
    ,’
    -0.06
     instancia
    -0.06
    crime
    -0.06
     ApplicationException
    -0.06
     economics
    -0.06
     unint
    -0.06
    iren
    -0.06
     улучш
    -0.06
    POSITIVE LOGITS
     opp
    0.08
    )(_
    0.07
    EMENT
    0.06
    抗
    0.06
     él
    0.06
     över
    0.06
     december
    0.06
     سر
    0.06
    ovit
    0.06
     erst
    0.06
    Act Density 0.054%

    No Known Activations