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

    Neuronpedia

    INDEX
    Explanations

    error occurred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.57
     inicialmente
    0.49
    ני
    0.47
    টির
    0.42
     Golpe
    0.42
     initially
    0.41
    টি
    0.41
    UAL
    0.40
    ーパー
    0.40
     partes
    0.39
    POSITIVE LOGITS
    t
    0.60
    ኋ
    0.46
     shall
    0.45
    将被
    0.45
     সমালোচনা
    0.43
    robot
    0.43
    */)
    0.42
    ت
    0.42
    <0x95>
    0.42
    摄影
    0.41
    Act Density 0.003%

    No Known Activations