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

    Neuronpedia

    INDEX
    Explanations

    mentions of study limitations and ethical considerations

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

    study limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kapture
    -0.43
    調查
    -0.42
    눗
    -0.42
    komna
    -0.42
     blur
    -0.40
     Ricardo
    -0.39
     fieldNum
    -0.39
    édia
    -0.39
     investigations
    -0.39
     Dorchester
    -0.39
    POSITIVE LOGITS
     limitations
    0.85
     implications
    0.78
    Implications
    0.77
     Limitations
    0.77
     limitation
    0.76
     Implications
    0.75
    Limitations
    0.75
    limitations
    0.69
     Limitation
    0.66
     LIMITATIONS
    0.65
    Act Density 0.337%

    No Known Activations