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

    Neuronpedia

    INDEX
    Explanations

    platform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਨਹੀਂ
    0.54
    Архі
    0.52
    ថ្ង
    0.52
    Confident
    0.52
    confident
    0.49
    uptime
    0.48
     다르
    0.48
    爌
    0.47
    石頭
    0.47
     เรียน
    0.47
    POSITIVE LOGITS
     reporter
    0.49
     posición
    0.46
     continued
    0.44
     Polo
    0.43
    த
    0.43
     politician
    0.41
     intervened
    0.41
    യിരുന്നു
    0.41
     Gav
    0.41
    न
    0.41
    Act Density 0.001%

    No Known Activations