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

    Neuronpedia

    INDEX
    Explanations

    thought experiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hythmic
    0.42
     सीटों
    0.40
    have
    0.40
    ingly
    0.39
    astly
    0.39
    ຄວ
    0.39
    制的
    0.39
     ভোট
    0.38
    ି
    0.37
    him
    0.37
    POSITIVE LOGITS
     processes
    0.84
     procesos
    0.76
     процессов
    0.76
     Processes
    0.75
     process
    0.73
     processos
    0.72
    processes
    0.70
     proceso
    0.70
     Prozesse
    0.70
     experiment
    0.70
    Act Density 0.021%

    No Known Activations