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

    Neuronpedia

    INDEX
    Explanations

    references to figures or illustrations within the document

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

    figure references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lics
    -0.57
    ———
    -0.51
    <bos>
    -0.51
     てる
    -0.50
    ald
    -0.48
    lda
    -0.47
    됐
    -0.47
    lids
    -0.47
    alds
    -0.47
    ds
    -0.46
    POSITIVE LOGITS
    Figure
    2.44
     Figure
    2.39
     Figura
    1.52
     FIGURE
    1.38
    Figura
    1.34
     Figures
    1.28
    FIGURE
    1.22
     Fig
    1.18
    Figures
    1.12
    Fig
    1.02
    Act Density 0.020%

    No Known Activations