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

    Neuronpedia

    INDEX
    Explanations

    references to figures and datasets in the document

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

    Figures with numbers

    np_acts-logits-general · gemini-2.0-flash

    figure numbers and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.83
    hamshire
    -0.78
    المناصب
    -0.78
    +#+
    -0.78
    ]--;
    -0.75
    CodeAttribute
    -0.75
     Chwiliwch
    -0.71
     Normdatei
    -0.70
    ----</
    -0.69
     للمعارف
    -0.67
    POSITIVE LOGITS
     below
    0.68
     shows
    0.66
     illustrates
    0.65
    (
    0.62
     depicts
    0.62
     left
    0.57
    a
    0.55
    below
    0.53
    next
    0.52
     inset
    0.51
    Act Density 0.646%

    No Known Activations