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

    Neuronpedia

    INDEX
    Explanations

    Louisville and John

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neglected
    0.38
    ']:
    0.37
     Dependent
    0.37
     kohta
    0.36
     optar
    0.36
    📩
    0.36
    काल
    0.36
     अजि
    0.35
    arlock
    0.35
     objectForKey
    0.35
    POSITIVE LOGITS
     Louisville
    1.25
    Louis
    1.05
    LOUIS
    0.91
     LOUIS
    0.90
     louis
    0.89
     Louis
    0.80
    ルイ
    0.70
    lou
    0.68
    Lou
    0.58
    LOUISE
    0.58
    Act Density 0.002%

    No Known Activations