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

    Neuronpedia

    INDEX
    Explanations

    occasionally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nye
    0.83
    changing
    0.81
     nya
    0.79
     changing
    0.79
     കൂടി
    0.77
     Changing
    0.77
     storm
    0.77
     crisis
    0.76
     újra
    0.75
     Yeni
    0.74
    POSITIVE LOGITS
     overall
    0.75
    Overall
    0.75
     Occasionally
    0.73
    有一些
    0.70
     Overall
    0.70
     irgendwo
    0.69
    цион
    0.68
    occas
    0.68
    Occasionally
    0.66
    कहीं
    0.66
    Act Density 0.228%

    No Known Activations