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

    Neuronpedia

    INDEX
    Explanations

    javascript module requires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prime
    0.86
     Peppers
    0.86
     Dep
    0.82
     Beans
    0.81
     Dim
    0.80
    TP
    0.80
     development
    0.80
     Widgets
    0.79
     Comun
    0.77
     Buccaneers
    0.77
    POSITIVE LOGITS
    direito
    0.88
    ..--
    0.79
    eradish
    0.73
    )"))
    0.73
    禣
    0.69
     любую
    0.68
     самую
    0.68
    bitro
    0.66
     conclure
    0.66
    .).
    0.66
    Act Density 0.001%

    No Known Activations