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

    Neuronpedia

    INDEX
    Explanations

    return/then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     _{
    0.49
    edit
    0.47
    neck
    0.44
    \}_{
    0.43
    ដូច
    0.43
    cheese
    0.43
    clothing
    0.43
    network
    0.43
    coins
    0.42
     himself
    0.42
    POSITIVE LOGITS
     балко
    0.52
     недвижимости
    0.46
    HERS
    0.46
    лм
    0.46
    Root
    0.44
    USION
    0.43
    0.43
     applicability
    0.42
    Мы
    0.42
    Holly
    0.41
    Act Density 0.004%

    No Known Activations