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

    Neuronpedia

    INDEX
    Explanations

    executes instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    目標
    0.50
    おり
    0.47
     Objetivo
    0.45
    ající
    0.45
    მატ
    0.43
    未來
    0.42
     sentimos
    0.42
     ?
    0.42
     Cor
    0.42
    特性
    0.41
    POSITIVE LOGITS
    k
    0.50
    Za
    0.46
    dr
    0.45
     adc
    0.45
    Ela
    0.45
    须知
    0.44
    4
    0.44
    ün
    0.44
     tackled
    0.44
     vasodil
    0.44
    Act Density 0.004%

    No Known Activations