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

    Neuronpedia

    INDEX
    Explanations

    must-see attractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     공
    0.53
     prompting
    0.52
     för
    0.48
     swing
    0.48
     Diwali
    0.47
    構
    0.46
     pacemaker
    0.46
    compiler
    0.46
    entwick
    0.45
    🥳
    0.45
    POSITIVE LOGITS
    usti
    0.54
     certeza
    0.52
     Ελλά
    0.50
    เซีย
    0.49
    intera
    0.49
    Italy
    0.49
    Entire
    0.48
    ドラゴン
    0.47
    <unused523>
    0.47
    THERS
    0.47
    Act Density 0.002%

    No Known Activations