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

    Neuronpedia

    INDEX
    Explanations

    classification levels and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ons
    0.41
     Decoding
    0.40
     என்பதே
    0.39
    厂
    0.39
     reun
    0.38
     :'
    0.38
    وجه
    0.38
     Raised
    0.37
     б
    0.37
     halls
    0.36
    POSITIVE LOGITS
    outputs
    0.47
     efficacious
    0.41
    efficacité
    0.40
    Cols
    0.39
    videos
    0.38
     discoveries
    0.38
     studies
    0.37
    ститут
    0.37
    studies
    0.37
     progen
    0.37
    Act Density 0.000%

    No Known Activations