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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     non
    0.70
     Non
    0.70
    0.66
    種類の
    0.64
     deren
    0.63
     ની
    0.62
     Clar
    0.61
     Take
    0.60
    চন্দ্রের
    0.60
     ne
    0.59
    POSITIVE LOGITS
     outweighs
    0.92
    🙄
    0.91
     منجر
    0.88
     despite
    0.88
     несмотря
    0.87
    ㅋㅋ
    0.87
     ㅋㅋ
    0.87
     malgré
    0.87
     lmao
    0.87
    💔
    0.85
    Act Density 0.171%

    No Known Activations