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

    Neuronpedia

    INDEX
    Explanations

    bolded answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    所谓
    0.42
    可能
    0.41
    0.40
    ?,?,
    0.38
     تانيه
    0.37
     solns
    0.36
    哪些
    0.36
    ,),
    0.36
    ঁচ
    0.35
     puissent
    0.35
    POSITIVE LOGITS
    <strong>
    0.99
    <b>
    0.87
     **
    0.79
     Generally
    0.55
     "**
    0.54
    >**
    0.52
    Generally
    0.48
    0.48
    mathbf
    0.47
    𝗚
    0.47
    Act Density 0.059%

    No Known Activations