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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     il
    0.85
     ferme
    0.74
     servi
    0.71
    ople
    0.70
    щаться
    0.69
    ల్యే
    0.69
    мены
    0.67
    moi
    0.66
    istos
    0.65
     Il
    0.65
    POSITIVE LOGITS
     بطور
    0.72
    LogRow
    0.62
     শত
    0.61
    <0xB4>
    0.60
     во
    0.60
    ્વ
    0.58
    ifend
    0.58
    QueueMutex
    0.57
     sua
    0.57
     won
    0.56
    Act Density 0.060%

    No Known Activations