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

    Neuronpedia

    INDEX
    Explanations

    studies and research findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     historical
    0.83
    Historical
    0.83
    historical
    0.81
     Historical
    0.78
     history
    0.77
    analytical
    0.75
    history
    0.75
     наука
    0.74
    ogy
    0.72
     historian
    0.71
    POSITIVE LOGITS
     सर्क
    0.82
     Jard
    0.72
    ScrollView
    0.71
     調
    0.70
    Random
    0.67
     Esc
    0.67
    複数の
    0.67
     Jardin
    0.66
     swallowed
    0.66
     حمل
    0.66
    Act Density 0.180%

    No Known Activations