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

    Neuronpedia

    INDEX
    Explanations

    cities and their contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.47
    }
    0.46
    L
    0.42
    \
    0.41
    P
    0.41
    D
    0.41
    {
    0.40
    F
    0.40
     I
    0.39
     dimensional
    0.37
    POSITIVE LOGITS
     metropolitan
    0.79
     città
    0.77
    <unused2184>
    0.76
     เมือง
    0.75
     unveils
    0.75
     welcomes
    0.74
     ನಗರ
    0.70
     suburbs
    0.69
    梩
    0.68
     SupCt
    0.68
    Act Density 0.224%

    No Known Activations