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

    Neuronpedia

    INDEX
    Explanations

    AI Chatbot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     highly
    0.71
     memories
    0.66
     enterprise
    0.65
     new
    0.64
     features
    0.64
     representatives
    0.64
     faithful
    0.64
     phrases
    0.62
     Highly
    0.60
     artificial
    0.60
    POSITIVE LOGITS
     ColumnName
    0.85
     സഹായി
    0.82
    writeInt
    0.78
    getColumnIndex
    0.77
    Edad
    0.76
    SetFloat
    0.75
    冠
    0.75
    Ꮑ
    0.74
    Tanggal
    0.74
    <unused23>
    0.74
    Act Density 0.157%

    No Known Activations