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

    Neuronpedia

    INDEX
    Explanations

    search algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sembra
    0.99
     informasjon
    0.95
     afge
    0.87
     effic
    0.84
     јед
    0.84
    ㄦ
    0.83
     axit
    0.83
    い
    0.83
     selezion
    0.82
     verrà
    0.82
    POSITIVE LOGITS
     Bus
    0.70
     Bat
    0.68
     Black
    0.68
     Expo
    0.66
     Olympics
    0.65
     Honours
    0.63
     Betting
    0.62
     Buses
    0.62
    silver
    0.62
    Wonder
    0.61
    Act Density 0.000%

    No Known Activations