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

    Neuronpedia

    INDEX
    Explanations

    Global configuration variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :#
    0.38
    <h5>
    0.38
    继承
    0.37
     chat
    0.37
    volution
    0.37
    ports
    0.37
     폭
    0.37
     DE
    0.37
     mass
    0.36
     hat
    0.36
    POSITIVE LOGITS
    ("%
    0.42
    ਫ਼
    0.40
    әне
    0.38
    ">/</
    0.38
     листья
    0.38
    纜
    0.38
     расскажу
    0.37
     связа
    0.37
     języ
    0.37
    swürdig
    0.37
    Act Density 0.000%

    No Known Activations