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

    Neuronpedia

    INDEX
    Explanations

    code/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addicted
    -0.07
    30
    -0.07
     Soc
    -0.06
     Psychology
    -0.06
     hạn
    -0.06
     basement
    -0.06
     crew
    -0.06
    01
    -0.06
    wa
    -0.06
     Recommend
    -0.06
    POSITIVE LOGITS
     нарез
    0.07
     Universe
    0.06
    .ArgumentParser
    0.06
    ritos
    0.06
     NSCoder
    0.06
    Executing
    0.06
    ])]
    0.06
    leş
    0.06
    ━━━━
    0.06
     gpu
    0.06
    Act Density 0.008%

    No Known Activations