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

    Neuronpedia

    INDEX
    Explanations

    surprisingly orderly and safe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     export
    0.43
     creating
    0.43
     internal
    0.42
     wewnętr
    0.42
    Boundary
    0.40
     original
    0.40
     boundary
    0.39
     anchor
    0.39
     neglected
    0.39
     créé
    0.39
    POSITIVE LOGITS
    治安
    0.73
    humidity
    0.68
     humidity
    0.67
     sidewalks
    0.64
    Humidity
    0.63
    cuisine
    0.63
     friendliness
    0.61
     Humidity
    0.61
     nightlife
    0.61
    房价
    0.60
    Act Density 0.025%

    No Known Activations