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

    Neuronpedia

    INDEX
    Explanations

    stumbled upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘆
    0.50
    و
    0.47
    hora
    0.44
    mappings
    0.42
    𝘦
    0.42
    ➣
    0.42
    િયાન
    0.42
    ‌ی
    0.41
    াপ
    0.41
    ্যানে
    0.40
    POSITIVE LOGITS
     stumble
    0.93
     stumbled
    0.93
     stumbling
    0.88
     encountered
    0.71
     препят
    0.67
     karşılaş
    0.64
     encountering
    0.64
     roadblocks
    0.63
     encounter
    0.63
     roadblock
    0.62
    Act Density 0.019%

    No Known Activations