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

    Neuronpedia

    INDEX
    Explanations

    and positive discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     требуется
    0.48
     requires
    0.48
     suggesting
    0.47
     எனவே
    0.43
    จึง
    0.42
    なので
    0.42
     forbidding
    0.40
     NON
    0.39
     suggests
    0.39
     يريد
    0.39
    POSITIVE LOGITS
     насла
    0.73
     enjoy
    0.72
     reap
    0.69
    enjoy
    0.68
     descobrir
    0.68
     discover
    0.68
     scoprire
    0.66
     yourself
    0.66
    享受
    0.65
     получите
    0.61
    Act Density 0.026%

    No Known Activations