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

    Neuronpedia

    INDEX
    Explanations

    anyone concerned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कहां
    0.39
    암
    0.39
     암
    0.38
    °-
    0.38
    負
    0.38
    ộn
    0.37
     دانلود
    0.37
     arrec
    0.37
     Nikki
    0.36
    総
    0.36
    POSITIVE LOGITS
     versions
    0.38
    pling
    0.37
    Provided
    0.37
     वातावर
    0.37
     सिन्हा
    0.37
     collaboration
    0.36
    物が
    0.36
     environment
    0.36
    herence
    0.36
     lasts
    0.36
    Act Density 0.004%

    No Known Activations