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

    Neuronpedia

    INDEX
    Explanations

    German scientists and philosophers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Portsmouth
    0.48
    🏴
    0.46
    परेशन
    0.45
    ኗ
    0.44
     ब्रिटेन
    0.43
     Southampton
    0.43
     Spaniards
    0.42
     Badajoz
    0.42
     Bournemouth
    0.42
    Montreal
    0.42
    POSITIVE LOGITS
     von
    0.80
     Heinrich
    0.74
     Wilhelm
    0.71
     Adolf
    0.70
     Johann
    0.70
    Heinrich
    0.67
     Georg
    0.65
    Johann
    0.64
    Georg
    0.61
     Friedrich
    0.61
    Act Density 0.005%

    No Known Activations