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

    Neuronpedia

    INDEX
    Explanations

    You mentioned you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    έργ
    0.48
     Dream
    0.46
     Novos
    0.45
     Cuenta
    0.45
     Agregar
    0.44
    áty
    0.44
     ड्रीम
    0.44
    йня
    0.43
    னின்
    0.42
     Realtors
    0.42
    POSITIVE LOGITS
    ０
    0.52
     boxing
    0.49
     ایمان
    0.48
     patrolling
    0.47
     waging
    0.47
     patience
    0.47
     fasting
    0.47
     victory
    0.46
    <td>
    0.46
     meditating
    0.46
    Act Density 0.002%

    No Known Activations