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

    Neuronpedia

    INDEX
    Explanations

    in the process of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    führ
    0.73
     Escal
    0.72
    arino
    0.71
     lectures
    0.71
    женер
    0.69
    ECT
    0.68
     cloned
    0.67
    愤
    0.67
     bhavanti
    0.67
    ট্রোল
    0.66
    POSITIVE LOGITS
     process
    3.64
    process
    3.35
    Process
    3.13
     Process
    3.11
     processo
    2.97
     proses
    2.95
     процесс
    2.93
     proceso
    2.89
     процессе
    2.82
    过程
    2.80
    Act Density 0.135%

    No Known Activations