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

    Neuronpedia

    INDEX
    Explanations

    technical terms followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ൊന്നും
    0.77
    ¬
    0.73
    Ã
    0.71
     simplesmente
    0.68
    <0xC2>
    0.68
    ረጋ
    0.68
    Which
    0.68
    လိုက်
    0.64
    which
    0.64
    alnız
    0.64
    POSITIVE LOGITS
    ).
    1.68
    }.
    1.59
    。
    1.58
    ।
    1.49
    ].
    1.47
    ’.
    1.44
    \}.
    1.42
    ،
    1.41
    ”.
    1.40
    (),
    1.38
    Act Density 0.265%

    No Known Activations