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

    Neuronpedia

    INDEX
    Explanations

    connections to historical or significant events and their implications

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

    GRID related code and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.82
     noDo
    -0.73
    RUnlock
    -0.69
     للمعارف
    -0.68
    OGND
    -0.66
     OMITBAD
    -0.65
    TagMode
    -0.65
    berdayakan
    -0.64
    rungsseite
    -0.63
    Autoritní
    -0.62
    POSITIVE LOGITS
    ↵↵
    0.40
    ↵↵↵
    0.38
    ↵
    0.38
     arī
    0.34
    </tr>
    0.33
     сви
    0.33
    The
    0.33
    า
    0.33
    This
    0.33
    <h3>
    0.32
    Act Density 24.703%

    No Known Activations