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

    Neuronpedia

    INDEX
    Explanations

    Rhys Stormblade, ZIP integrity, HOME directory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     butterfly
    0.45
     butterflies
    0.42
     shoes
    0.42
     skulls
    0.41
     ഓഫീ
    0.41
     illusion
    0.40
     puppies
    0.39
     officer
    0.39
     vertex
    0.39
     headsets
    0.39
    POSITIVE LOGITS
    觟
    0.43
    filename
    0.42
    beliefs
    0.40
    Dans
    0.40
    ests
    0.39
    ('-');
    0.39
     Franks
    0.38
    Completion
    0.38
    ussen
    0.38
    Programme
    0.37
    Act Density 0.000%

    No Known Activations