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

    Neuronpedia

    INDEX
    Explanations

    programming function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fileTool
    0.69
     Inventors
    0.68
     legislation
    0.67
     inventions
    0.66
     particle
    0.66
    jenis
    0.65
    淍
    0.65
     polymorphism
    0.64
     industries
    0.64
    industry
    0.63
    POSITIVE LOGITS
    Async
    0.84
    robust
    0.64
    )
    0.64
     Robust
    0.62
    Fun
    0.62
    From
    0.62
    φέ
    0.61
     robust
    0.61
     _)
    0.60
    Ab
    0.60
    Act Density 0.083%

    No Known Activations