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

    Neuronpedia

    INDEX
    Explanations

    references to uniqueness and standout characteristics within a group

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

    Follows ordinal numbers/comparatives

    np_acts-logits-general · gemini-2.0-flash

    among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OCCURRED
    -0.62
    CodeAttribute
    -0.58
     />,
    -0.57
    apimachinery
    -0.52
    #![
    -0.51
    </thead>
    -0.49
    原始内容存档于
    -0.48
    veland
    -0.48
    cou
    -0.47
    jsdelivr
    -0.46
    POSITIVE LOGITS
     among
    0.91
     amongst
    0.89
    among
    0.85
     AMONG
    0.79
     Amongst
    0.75
     среди
    0.70
     Among
    0.68
    Among
    0.67
     parmi
    0.62
     wśród
    0.60
    Act Density 0.245%

    No Known Activations