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

    Neuronpedia

    INDEX
    Explanations

    every time / whenever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এরই
    0.54
     altri
    0.52
     प्रकारचे
    0.50
    মধ্যেই
    0.49
    Là
    0.49
     años
    0.48
     próprios
    0.47
     Là
    0.47
     creciendo
    0.46
     рит
    0.46
    POSITIVE LOGITS
    每次
    0.72
     Whenever
    0.70
    whenever
    0.67
    Whenever
    0.66
    마다
    0.63
    li
    0.59
    kita
    0.58
     whenever
    0.57
    每一次
    0.55
    遇到
    0.53
    Act Density 0.015%

    No Known Activations