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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating geographical or spatial references

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

    parts of various entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jamento
    -0.40
     Paragu
    -0.38
     garanti
    -0.37
     endblock
    -0.37
    orcid
    -0.36
    ApiOperation
    -0.36
    daille
    -0.36
    impanan
    -0.36
    Proven
    -0.35
     Maltese
    -0.35
    POSITIVE LOGITS
     parts
    0.72
     Teile
    0.65
     regions
    0.65
     muualla
    0.62
     elsewhere
    0.61
    各地
    0.60
     Parts
    0.59
     PARTS
    0.59
     across
    0.58
     areas
    0.58
    Act Density 0.016%

    No Known Activations