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

    Neuronpedia

    INDEX
    Explanations

    introduces specific items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ED
    0.62
    0.54
     https
    0.51
    S
    0.49
     temp
    0.48
     biom
    0.48
    ID
    0.47
     enzyme
    0.47
    、
    0.46
     http
    0.45
    POSITIVE LOGITS
    то
    0.72
     прозра
    0.64
     процен
    0.64
     関係
    0.62
     процент
    0.62
     diámetro
    0.61
    тро
    0.61
    нт
    0.61
    лад
    0.61
    ро
    0.60
    Act Density 0.000%

    No Known Activations