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

    Neuronpedia

    INDEX
    Explanations

    How can I help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ze
    0.46
    ५
    0.45
    went
    0.43
    basically
    0.43
    eduanya
    0.42
     मुताबिक
    0.42
     Interment
    0.41
    rzez
    0.41
     UNNEEDED
    0.40
    Have
    0.40
    POSITIVE LOGITS
    。
    0.46
     but
    0.44
     escolares
    0.44
          
    0.43
     shall
    0.42
     för
    0.41
     \
    0.41
        
    0.41
     رؤ
    0.40
     nhưng
    0.40
    Act Density 0.003%

    No Known Activations