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

    Neuronpedia

    INDEX
    Explanations

    as many as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    槭
    0.37
     doesnt
    0.35
     इलेक्ट्रॉनिक
    0.35
     BUFFER
    0.35
    िस्थित
    0.35
     электрон
    0.35
     Ihres
    0.34
     wouldnt
    0.34
     Име
    0.34
    疖
    0.34
    POSITIVE LOGITS
     well
    0.38
    df
    0.37
     much
    0.36
    ពិសេស
    0.35
    warm
    0.34
     triumphant
    0.34
     nefarious
    0.34
     sinister
    0.34
     warm
    0.33
     absurd
    0.33
    Act Density 0.000%

    No Known Activations