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

    Neuronpedia

    INDEX
    Explanations

    how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uitle
    0.77
     توضی
    0.76
    講解
    0.72
     spieg
    0.70
     statement
    0.69
     explanation
    0.68
    代码
    0.67
    注释
    0.67
     justification
    0.67
     설명
    0.67
    POSITIVE LOGITS
     emerging
    0.70
    gob
    0.62
     laquelle
    0.62
     داخ
    0.61
    Running
    0.59
    iah
    0.59
    );//
    0.59
     тог
    0.58
     внутреннего
    0.57
    That
    0.57
    Act Density 0.039%

    No Known Activations