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

    Neuronpedia

    INDEX
    Explanations

    acting in context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h2>
    0.56
    tor
    0.44
    </h4>
    0.44
     Tanaka
    0.42
    tr
    0.42
    secret
    0.41
    rendered
    0.41
    pg
    0.41
     Zone
    0.41
    ll
    0.40
    POSITIVE LOGITS
     вдох
    0.54
     dát
    0.50
     प्रजनन
    0.49
     dernière
    0.49
     возь
    0.49
     공동
    0.48
     التأ
    0.48
     차
    0.47
    ྥ
    0.47
     अद्भ
    0.46
    Act Density 0.001%

    No Known Activations