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

    Neuronpedia

    INDEX
    Explanations

    Capitalized "Graves"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     తెర
    0.38
     constructs
    0.37
     tonnage
    0.37
     crass
    0.37
     copying
    0.36
     sacs
    0.36
     Issa
    0.36
     boiling
    0.36
     ensembles
    0.35
     mane
    0.35
    POSITIVE LOGITS
    Ded
    0.50
    DES
    0.49
     Ded
    0.47
     значительно
    0.45
    Про
    0.42
     exercises
    0.42
     существенно
    0.42
    exercises
    0.41
     ded
    0.41
     DES
    0.41
    Act Density 0.000%

    No Known Activations