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

    Neuronpedia

    INDEX
    Explanations

    points escalated lock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ポルト
    0.48
     ಕ್ರ
    0.45
     mencion
    0.44
     வெங்க
    0.44
     २०२
    0.44
     نقصان
    0.42
    ▮
    0.42
    棪
    0.42
     ಇನ್ನ
    0.41
     ಹಣ
    0.41
    POSITIVE LOGITS
     wasn
    0.48
     socket
    0.47
     begins
    0.46
     customized
    0.45
     appears
    0.42
     sutures
    0.42
     often
    0.41
     meestal
    0.41
     reaches
    0.41
     usually
    0.40
    Act Density 0.012%

    No Known Activations