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

    Neuronpedia

    INDEX
    Explanations

    services, incentives, advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unate
    0.47
    nesses
    0.47
    greeting
    0.46
    un
    0.45
    skip
    0.45
    ns
    0.44
    BANK
    0.44
    begin
    0.43
    inhib
    0.43
    inction
    0.43
    POSITIVE LOGITS
     veículos
    0.50
     Producto
    0.47
     mexicano
    0.47
     başka
    0.46
     önceki
    0.46
    ມາ
    0.46
     mach
    0.46
     macchina
    0.46
    ുമു
    0.46
     descubrir
    0.45
    Act Density 0.003%

    No Known Activations