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

    Neuronpedia

    INDEX
    Explanations

    programming code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bsky
    0.40
    thiophen
    0.39
    usions
    0.37
     अनुश
    0.36
    sulph
    0.35
    ರವ
    0.35
    ropolit
    0.35
    磡
    0.35
    ｵ
    0.34
    сар
    0.34
    POSITIVE LOGITS
    <h2>
    0.43
    ↵
    0.40
     kullanılır
    0.40
    !
    0.38
    ”
    0.38
     But
    0.37
    ...
    0.37
    </tr>
    0.36
     Jdbc
    0.36
    .”
    0.35
    Act Density 0.036%

    No Known Activations