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

    Neuronpedia

    INDEX
    Explanations

    jokes and riddles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quasi
    0.46
     restre
    0.42
    ்துற
    0.41
     자체
    0.40
    귿
    0.40
    ᵐ
    0.40
    有着
    0.40
     envo
    0.39
    ⚒
    0.39
     கட்டமை
    0.38
    POSITIVE LOGITS
    টিক
    0.44
     blonde
    0.43
     chiese
    0.43
     bushes
    0.43
     জিজ্ঞাসা
    0.43
     wife
    0.42
     জিজ্ঞেস
    0.42
     Rhodesia
    0.42
     astonished
    0.42
    getBoolean
    0.42
    Act Density 0.148%

    No Known Activations