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

    Neuronpedia

    INDEX
    Explanations

    com.example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emeni
    0.88
    Asp
    0.87
     ainult
    0.84
     दंप
    0.79
    捍
    0.79
    linkedExternal
    0.79
    elizmente
    0.76
    issante
    0.76
    andowski
    0.76
    SSFWorkbook
    0.75
    POSITIVE LOGITS
     Create
    0.84
     Laptop
    0.76
     Creates
    0.75
     sour
    0.75
     Beat
    0.74
     Guy
    0.72
     guy
    0.72
    وفيق
    0.71
    ajt
    0.71
     Созда
    0.69
    Act Density 0.000%

    No Known Activations