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

    Neuronpedia

    INDEX
    Explanations

    Safety, injury, Pokemon, FPS, Cloud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étrang
    0.45
     સ્થ
    0.41
    ກະ
    0.39
    പി
    0.39
    foreign
    0.38
    destination
    0.38
    曜日
    0.38
    location
    0.37
     destination
    0.37
    special
    0.37
    POSITIVE LOGITS
     Judd
    0.41
     தச
    0.40
     Parkland
    0.40
     Huddersfield
    0.40
    Grady
    0.40
     Someone
    0.39
     Dumping
    0.39
     transforming
    0.39
     Grady
    0.39
     riff
    0.39
    Act Density 0.001%

    No Known Activations