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

    Neuronpedia

    INDEX
    Explanations

    patterns of punctuation and formatting in the document

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

    scientific references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✨:
    -0.40
     ataques
    -0.34
    protetor
    -0.32
    ləş
    -0.31
     réve
    -0.31
    GEBURTS
    -0.31
     attribué
    -0.30
    exitRule
    -0.30
    attack
    -0.30
    GOTREF
    -0.30
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
    ⟭
    0.51
    NSIndexPath
    0.51
    ⪜
    0.50
    الحياه
    0.50
    WriteTagHelper
    0.50
    #+#
    0.50
    //}
    0.49
    ⟬
    0.49
    Попис
    0.48
    Act Density 0.014%

    No Known Activations