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

    Neuronpedia

    INDEX
    Explanations

    animal class constructor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    convén
    0.44
     স্থগিত
    0.44
    人物
    0.43
    াকিব
    0.42
     स्थगित
    0.41
    酴
    0.41
    ாளர்
    0.40
    信用卡
    0.40
     pessim
    0.40
     demons
    0.40
    POSITIVE LOGITS
     habitat
    0.88
     mating
    0.82
     feeding
    0.81
     claws
    0.80
     habitats
    0.80
     eats
    0.78
     breed
    0.75
     docile
    0.75
     eat
    0.73
     breeding
    0.73
    Act Density 0.045%

    No Known Activations