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

    Neuronpedia

    INDEX
    Explanations

    geographical locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ψ
    0.42
     psico
    0.42
     각종
    0.41
     text
    0.40
     ψ
    0.40
     combust
    0.39
    Constit
    0.39
    爻
    0.38
     thresh
    0.38
     PIC
    0.38
    POSITIVE LOGITS
     London
    1.71
     Germany
    1.61
     Toronto
    1.59
     Australia
    1.55
     Mumbai
    1.48
     California
    1.48
     Italy
    1.48
     Tokyo
    1.47
     Canada
    1.46
     لندن
    1.46
    Act Density 0.020%

    No Known Activations