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

    Neuronpedia

    INDEX
    Explanations

    Python Professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ців
    0.53
    acetone
    0.49
    ata
    0.47
    entropic
    0.47
    uscular
    0.47
    ag
    0.46
    amide
    0.46
     الدهون
    0.46
    cystic
    0.46
     painkillers
    0.46
    POSITIVE LOGITS
     attraction
    0.47
     activate
    0.47
    銮
    0.46
     idios
    0.46
     argent
    0.46
     respond
    0.44
     capitalize
    0.44
     auxili
    0.44
     associating
    0.44
     overload
    0.43
    Act Density 0.001%

    No Known Activations