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

    Neuronpedia

    INDEX
    Explanations

    import statement keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ic
    0.81
    αν
    0.78
    ৮
    0.76
    ер
    0.75
    ৪
    0.75
    ар
    0.74
     {'
    0.74
    स
    0.73
    LOVE
    0.72
    هههه
    0.71
    POSITIVE LOGITS
    লেখ
    0.75
     posits
    0.73
     microtubules
    0.73
     zakresie
    0.70
    ați
    0.70
     आल्या
    0.69
     varietà
    0.69
     obscures
    0.68
     বিরত
    0.68
     matroid
    0.68
    Act Density 0.001%

    No Known Activations