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

    Neuronpedia

    INDEX
    Explanations

    instructions, requirements, and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused734>
    0.44
    Ꮐ
    0.42
    玖章
    0.42
    ૪
    0.42
     houve
    0.41
    <unused277>
    0.41
    പാട്
    0.40
    <unused733>
    0.40
    ൽ
    0.38
    齙
    0.38
    POSITIVE LOGITS
    .”
    0.57
    ).
    0.52
    ."
    0.52
    :
    0.52
     but
    0.51
    .)
    0.50
    ".
    0.50
    。
    0.49
     And
    0.49
    .
    0.49
    Act Density 0.057%

    No Known Activations