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

    Neuronpedia

    INDEX
    Explanations

    you can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     casinos
    0.47
     Casinos
    0.43
     vaccines
    0.42
     Casino
    0.42
     بودند
    0.39
    Loan
    0.39
    などで
    0.39
     কেন্দ্রে
    0.39
     watchers
    0.39
     nightclubs
    0.39
    POSITIVE LOGITS
     elm
    0.38
     tanda
    0.38
    önig
    0.38
     اگر
    0.38
    りの
    0.37
                         
    0.37
    ().__
    0.37
    ┈┈
    0.37
    0.37
    ්
    0.36
    Act Density 0.000%

    No Known Activations