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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oblig
    0.40
    scaron
    0.39
    の使い方
    0.38
     ব্যবহারের
    0.38
    ijek
    0.37
     ingeniero
    0.36
    」(
    0.36
    engelsk
    0.36
     হবার
    0.36
     şirk
    0.36
    POSITIVE LOGITS
    鑊
    0.38
     velit
    0.38
     Alonzo
    0.38
    רום
    0.37
     Anak
    0.37
     පිළ
    0.37
    Mission
    0.37
    віда
    0.36
    Load
    0.36
    Wra
    0.36
    Act Density 0.000%

    No Known Activations