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

    Neuronpedia

    INDEX
    Explanations

    vicuna delta weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bed
    0.51
    kil
    0.49
    BED
    0.48
    concrete
    0.48
    Obes
    0.48
    calculated
    0.47
    agricultural
    0.47
    ॉक्स
    0.47
    fireplace
    0.46
    myItemId
    0.46
    POSITIVE LOGITS
    ！
    0.51
    ？
    0.48
     semestre
    0.46
    "。
    0.46
     recruiter
    0.46
     ves
    0.45
     것은
    0.43
     sempre
    0.43
     vests
    0.42
     Alexandria
    0.42
    Act Density 0.001%

    No Known Activations