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

    Neuronpedia

    INDEX
    Explanations

    natural phenomena and things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vítima
    0.37
     اسے
    0.34
     dość
    0.33
     två
    0.32
     ühe
    0.32
     triglyceride
    0.31
     AppDelegate
    0.31
     sintomas
    0.31
     ہے۔
    0.30
     kanya
    0.30
    POSITIVE LOGITS
     galore
    0.67
    cheduling
    0.50
    なども
    0.49
     and
    0.46
    ri
    0.46
     etc
    0.45
    etc
    0.45
    -
    0.44
    ih
    0.43
    um
    0.43
    Act Density 0.437%

    No Known Activations