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

    Neuronpedia

    INDEX
    Explanations

    all-domain resolution office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arang
    0.54
     klub
    0.52
    </h3>
    0.51
    lebih
    0.50
     semangat
    0.49
     tiap
    0.48
     club
    0.48
     damos
    0.47
    arie
    0.47
    tidak
    0.46
    POSITIVE LOGITS
     Fate
    0.53
    ות
    0.52
    障
    0.52
    Fate
    0.51
     Hark
    0.51
    障害
    0.50
    境
    0.48
    NRC
    0.48
    मिला
    0.48
    葶
    0.47
    Act Density 0.001%

    No Known Activations