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

    Neuronpedia

    INDEX
    Explanations

    street and address components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.73
    ．
    0.64
     .
    0.62
    流程
    0.62
     ataque
    0.62
    ש
    0.61
     Populations
    0.61
    SI
    0.59
    9
    0.59
    1
    0.58
    POSITIVE LOGITS
     boulevard
    1.07
     улице
    1.02
     street
    0.94
     вули
    0.88
     Boulevard
    0.86
     улица
    0.86
     Street
    0.85
     avenue
    0.84
     streets
    0.83
     거리
    0.79
    Act Density 0.043%

    No Known Activations