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

    Neuronpedia

    INDEX
    Explanations

    Netherlands and Belgium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nant
    1.01
    u
    1.00
    એ
    0.97
    uje
    0.95
    かけ
    0.93
    ɰ
    0.93
    トップ
    0.92
    效率
    0.89
    మన్
    0.89
    o
    0.89
    POSITIVE LOGITS
    ী
    1.08
     Sacrament
    0.97
     РАН
    0.89
     mưa
    0.88
    dures
    0.88
     Согласно
    0.88
    ្សែ
    0.86
    Senha
    0.85
    Eksterne
    0.84
     Courthouse
    0.83
    Act Density 0.002%

    No Known Activations