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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    punctuation followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.63
    PerformLayout
    -0.58
     väli
    -0.52
    yntaxException
    -0.51
    şört
    -0.51
    Bakgrunnsstoff
    -0.50
     ब्रेकडाउन
    -0.49
    évaluateur
    -0.48
    fillType
    -0.48
    colla
    -0.45
    POSITIVE LOGITS
    서는
    0.52
     its
    0.52
    은
    0.51
    는
    0.50
    하면
    0.47
    は
    0.46
     هي
    0.46
    家は
    0.45
    在
    0.45
    하여
    0.44
    Act Density 0.008%

    No Known Activations