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

    Neuronpedia

    INDEX
    Explanations

    explanation and definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *
    1.66
    <strong>
    1.54
    <code>
    1.35
    <ul>
    1.32
    ↵↵↵
    1.28
    ·
    1.25
    <h6>
    1.24
    ↵↵↵↵↵↵↵↵↵↵↵
    1.18
    ●
    1.16
    <h3>
    1.14
    POSITIVE LOGITS
    .)..
    0.76
    ᆹ
    0.74
    ..)
    0.74
    )....
    0.74
    ፂ
    0.73
    CacheV
    0.73
    ྡ
    0.72
    坭
    0.72
     "/")
    0.71
    桷
    0.71
    Act Density 0.357%

    No Known Activations