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

    Neuronpedia

    INDEX
    Explanations

    references to specific software and tools in technical contexts

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

    notes followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.49
     Superhost
    -0.44
     communs
    -0.44
    ammans
    -0.43
     económicas
    -0.42
     claro
    -0.42
     Kerajaan
    -0.40
     sanitaires
    -0.40
     universelle
    -0.40
     commerciaux
    -0.40
    POSITIVE LOGITS
     note
    0.90
     notes
    0.85
     Notes
    0.83
     Note
    0.78
    Note
    0.76
    note
    0.71
     NOTES
    0.70
    Datuak
    0.69
    Notes
    0.69
    notes
    0.69
    Act Density 0.011%

    No Known Activations