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

    Neuronpedia

    INDEX
    Explanations

    predicting compatibility of libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.52
     Draft
    0.49
    Draft
    0.49
     Marketing
    0.48
    Marketing
    0.47
    Sp
    0.45
    I
    0.44
     Resources
    0.43
    ล
    0.43
    IFS
    0.42
    POSITIVE LOGITS
     laborer
    0.52
     mediante
    0.48
     anului
    0.46
    jenje
    0.43
     faq
    0.43
     idealistic
    0.43
     gewisse
    0.43
     spoloč
    0.43
    வ்வாறு
    0.42
     hinder
    0.42
    Act Density 0.003%

    No Known Activations