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

    Neuronpedia

    INDEX
    Explanations

    increases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     진행
    -0.08
     dati
    -0.08
    _hostname
    -0.08
     વિગતો
    -0.08
    سماء
    -0.08
     initialization
    -0.08
    _initialized
    -0.07
     magaca
    -0.07
     zar
    -0.07
    کان
    -0.07
    POSITIVE LOGITS
    徒歩
    0.12
     commuter
    0.11
     pedestrian
    0.11
     corridors
    0.10
     urban
    0.10
     commuters
    0.10
     pedestrians
    0.10
    交通
    0.10
     corridor
    0.10
     passenger
    0.09
    Act Density 0.032%

    No Known Activations